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

    Neuronpedia

    INDEX
    Explanations

    emotional reactions and responses

    oai_token-act-pair · gpt-3.5-turbo

    expressions of strong negative emotions and reactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vernment
    -0.74
    vre
    -0.71
    natureconservancy
    -0.70
     Flavoring
    -0.69
    imum
    -0.68
    ramids
    -0.68
     penet
    -0.68
    Quant
    -0.67
    UA
    -0.66
    iatures
    -0.66
    POSITIVE LOGITS
     saddened
    1.08
     disappointed
    0.95
     disillusion
    0.93
     frustrated
    0.92
     embarrassed
    0.92
     dismay
    0.91
     humiliated
    0.87
     angry
    0.87
     appalled
    0.87
     nervous
    0.86
    Act Density 0.393%

    No Known Activations