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

    Neuronpedia

    INDEX
    Explanations

    positive adjectives describing things or actions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "impressive" as well as related expressions of admiration or praise

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ©¶æ
    -0.80
    sole
    -0.79
    opter
    -0.71
    uter
    -0.71
    sol
    -0.70
    nav
    -0.70
    foreseen
    -0.67
    ajor
    -0.67
    ________
    -0.67
    iche
    -0.66
    POSITIVE LOGITS
     feats
    1.04
     feat
    1.03
     accomplishment
    0.91
    issance
    0.90
     accomplishments
    0.82
     achievement
    0.80
     enough
    0.77
    ments
    0.75
     impressive
    0.74
     victories
    0.71
    Act Density 0.021%

    No Known Activations