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

    Neuronpedia

    INDEX
    Explanations

    words related to strong feelings or wishes

    oai_token-act-pair · gpt-3.5-turbo

    expressions of desire

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Surv
    -0.86
    avis
    -0.72
    ocular
    -0.72
    annis
    -0.71
    mans
    -0.69
    uum
    -0.68
    stood
    -0.68
    marg
    -0.66
     Dispatch
    -0.66
     Solitaire
    -0.65
    POSITIVE LOGITS
     fulfillment
    0.95
    lessly
    0.90
     fulfilled
    0.83
    igslist
    0.82
    00200000
    0.80
    rence
    0.80
    ful
    0.78
    urable
    0.77
    reprene
    0.77
     fulfil
    0.74
    Act Density 0.026%

    No Known Activations