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

    Neuronpedia

    INDEX
    Explanations

    statements or reports issued by individuals or organizations

    oai_token-act-pair · gpt-3.5-turbo

    references to formal communications, such as statements, reports, and letters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Authors
    -0.71
    icides
    -0.65
    wick
    -0.61
    nor
    -0.59
     Fees
    -0.58
     fades
    -0.55
     Decay
    -0.55
    ances
    -0.55
    dos
    -0.54
     Dates
    -0.54
    POSITIVE LOGITS
     alleging
    1.26
     stating
    1.26
     titled
    1.22
     detailing
    1.21
     outlining
    1.20
     accusing
    1.20
     claiming
    1.19
     apologizing
    1.18
     saying
    1.17
     praising
    1.15
    Act Density 0.230%

    No Known Activations