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

    Neuronpedia

    INDEX
    Explanations

    words related to the concept of 'action'

    oai_token-act-pair · gpt-3.5-turbo

    terms related to legal infractions and their consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    çĦ
    -0.73
     bes
    -0.67
     bro
    -0.66
     schemes
    -0.65
     live
    -0.65
     Mel
    -0.63
     advice
    -0.63
     grips
    -0.63
     Cyrus
    -0.62
     mourn
    -0.60
    POSITIVE LOGITS
    raction
    4.40
    ractions
    3.55
    racted
    2.67
    ractive
    2.15
    ract
    2.04
    ractor
    2.03
    lux
    1.18
    inction
    1.17
    ulsion
    1.16
    iltration
    1.03
    Act Density 0.013%

    No Known Activations