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

    Neuronpedia

    INDEX
    Explanations

    dialogue and interactions between characters in a narrative

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

    Punctuation followed by a word

    np_acts-logits-general · gemini-2.0-flash

    actions and descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IsContent
    -0.73
    ьаж
    -0.69
    TagMode
    -0.69
    SBATCH
    -0.67
    Personensuche
    -0.65
    rophes
    -0.65
     يتيمه
    -0.65
    ParallelGroup
    -0.65
    رشف
    -0.62
    UnusedPrivate
    -0.62
    POSITIVE LOGITS
    ionine
    0.49
     saying
    0.46
    haus
    0.46
     dist
    0.46
    udo
    0.45
    AnchorStyles
    0.45
     whispers
    0.44
    CompleteListener
    0.44
    NextPage
    0.43
     said
    0.43
    Act Density 0.133%

    No Known Activations