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

    Neuronpedia

    INDEX
    Explanations

    references to urgency or immediacy

    oai_token-act-pair · gpt-3.5-turbo

    terms related to immediate effects or consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cius
    -0.84
    acus
    -0.78
    doctor
    -0.76
    ingers
    -0.74
    glers
    -0.74
    _-
    -0.73
    ramids
    -0.71
     Conduct
    -0.69
    leck
    -0.68
    MET
    -0.68
    POSITIVE LOGITS
    aneously
    1.29
     gratification
    1.16
    izable
    0.85
    aneous
    0.84
     immediate
    0.84
     aftermath
    0.82
    motion
    0.76
     reaction
    0.76
    mediate
    0.74
     overflow
    0.73
    Act Density 0.013%

    No Known Activations