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

    Neuronpedia

    INDEX
    Explanations

    words related to amazement or astonishment

    oai_token-act-pair · gpt-3.5-turbo

    words related to being impressed or astonished

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    女
    -0.68
     mend
    -0.60
    itimate
    -0.60
     equ
    -0.58
    abor
    -0.56
    ocratic
    -0.55
     hone
    -0.55
     crops
    -0.55
     Boh
    -0.54
    onduct
    -0.54
    POSITIVE LOGITS
    azed
    1.10
    aze
    1.07
    aughs
    0.85
    ecake
    0.84
    geoning
    0.82
    azing
    0.81
    ï¸
    0.80
     Decay
    0.80
    urous
    0.78
    eker
    0.77
    Act Density 0.007%

    No Known Activations