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

    Neuronpedia

    INDEX
    Explanations

    expressions related to willingness, desire, and motivation towards certain actions or behaviors

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to readiness and desire for action or change

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Surv
    -1.03
     Wrap
    -0.83
    MpServer
    -0.77
     Grac
    -0.71
     Gleaming
    -0.71
    daq
    -0.69
    DAQ
    -0.68
    icle
    -0.66
    Interstitial
    -0.65
    icles
    -0.65
    POSITIVE LOGITS
     willingness
    0.73
    lessness
    0.73
    rence
    0.73
    irection
    0.72
     fatigue
    0.72
     thirst
    0.70
     adherence
    0.70
     cooker
    0.70
     appetite
    0.70
    ossibility
    0.70
    Act Density 0.101%

    No Known Activations