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

    Neuronpedia

    INDEX
    Explanations

    words related to abstract concepts or situations that have potential consequences

    oai_token-act-pair · gpt-3.5-turbo

    terms related to negative societal behaviors and medical conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     largeDownload
    -0.71
    liquid
    -0.61
    cham
    -0.60
    rollers
    -0.59
     instinctively
    -0.59
     âĨij
    -0.58
    llan
    -0.58
     Reincarn
    -0.57
    BOOK
    -0.57
    lli
    -0.57
    POSITIVE LOGITS
    ity
    3.12
    ities
    2.56
    ITY
    1.94
    ization
    1.87
    ité
    1.84
    izing
    1.82
    ITIES
    1.78
    ized
    1.77
    itous
    1.77
    ties
    1.75
    Act Density 0.181%

    No Known Activations