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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating regret or warning signs related to decisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zel
    -0.16
     descon
    -0.14
    .openg
    -0.14
    -wow
    -0.13
    endar
    -0.13
    .mx
    -0.13
    OfYear
    -0.13
    ãģ£
    -0.13
    ampo
    -0.13
    òn
    -0.13
    POSITIVE LOGITS
     signs
    0.84
     Signs
    0.71
     sign
    0.68
     signals
    0.59
    sign
    0.59
     indicators
    0.56
     signal
    0.55
     indication
    0.55
     indications
    0.55
    Sign
    0.54
    Act Density 0.279%

    No Known Activations