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

    Neuronpedia

    INDEX
    Explanations

    adjectives describing the intensity or importance of specific attributes

    oai_token-act-pair · gpt-3.5-turbo

    adjectives and adverbs conveying strong negative or evaluative sentiments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     DRAG
    -0.70
    azo
    -0.61
    asio
    -0.61
    ynski
    -0.60
    cision
    -0.57
     Flavoring
    -0.57
    adish
    -0.56
     Vaults
    -0.56
    omething
    -0.56
     BF
    -0.55
    POSITIVE LOGITS
    haus
    0.77
    accessible
    0.66
     unatt
    0.66
     ripe
    0.63
    rongh
    0.63
    hit
    0.61
    readable
    0.60
    vind
    0.60
    competitive
    0.60
     unsustainable
    0.59
    Act Density 0.245%

    No Known Activations