Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases or concepts related to continuity, transition, or connection between ideas or actions. It seems to activate strongly for words and phrases that link or relate different parts of a sentence or passage, especially when describing processes, sequences, or relationships between concepts.

    oai_token-act-pair · claude-3-5-sonnet-20240620Triggered by @myinzi123

    discussions related to personal relationships and social interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Text after function words or punctuation

    np_acts-logits-general · gemini-2.0-flash

    make a decision

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Económica
    -0.43
    ValueStyle
    -0.42
    transQ
    -0.40
     stimmen
    -0.40
     élo
    -0.39
    ambilan
    -0.39
    Vidite
    -0.38
    Архівовано
    -0.38
    ubehör
    -0.37
    KommentareTeilen
    -0.36
    POSITIVE LOGITS
     SDLK
    0.44
    MigrationBuilder
    0.44
    msgTypes
    0.44
    quatch
    0.43
     Winaray
    0.42
     JPanel
    0.41
    walkers
    0.41
    GLuint
    0.41
    ettür
    0.41
    MessageOf
    0.41
    Act Density 0.770%

    No Known Activations