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

    Neuronpedia

    INDEX
    Explanations

    words related to specific fields of study or expertise, particularly with a focus on '-ics' suffix

    oai_token-act-pair · gpt-3.5-turbo

    references to scientific fields and disciplines

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    LET
    -0.68
     proportion
    -0.67
     felon
    -0.66
     Cord
    -0.65
    legged
    -0.64
     funnel
    -0.60
     undefined
    -0.59
     guaranteed
    -0.58
     unaccount
    -0.58
     overw
    -0.58
    POSITIVE LOGITS
    ics
    4.54
    ICS
    2.30
    icism
    2.15
    ically
    1.91
    ic
    1.88
    ical
    1.78
    icals
    1.77
    ICAL
    1.56
    icians
    1.55
    icity
    1.55
    Act Density 0.013%

    No Known Activations