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

    Neuronpedia

    INDEX
    Explanations

    sentences with personal reflections and emotions

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

    Follows personal pronouns or proper nouns

    np_acts-logits-general · gemini-2.0-flash

    for me

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     rodea
    -0.47
    ismes
    -0.46
     архивлан
    -0.46
     TextAppearance
    -0.41
    MigrationBuilder
    -0.40
    isteria
    -0.40
     FRAG
    -0.39
    仗
    -0.39
    ableness
    -0.39
    BufferException
    -0.38
    POSITIVE LOGITS
    UserScript
    0.43
    にとって
    0.42
     számára
    0.41
     mapStateToProps
    0.41
    にとっては
    0.40
    bkz
    0.40
    发表于
    0.40
    >//
    0.40
    enumi
    0.39
     بالنسبة
    0.39
    Act Density 0.517%

    No Known Activations