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

    Neuronpedia

    INDEX
    Explanations

    terms and agreements mentioned in documents

    oai_token-act-pair · gpt-3.5-turbo

    references to terms of use or service agreements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    idis
    -0.81
    acid
    -0.78
    ï¸ı
    -0.73
     Cros
    -0.72
    usercontent
    -0.71
    ÃŃs
    -0.71
    aceae
    -0.70
    iens
    -0.67
    waukee
    -0.67
    enne
    -0.67
    POSITIVE LOGITS
     probation
    0.86
     lease
    0.83
     truce
    0.75
     tenancy
    0.73
     legality
    0.73
     compensation
    0.73
     confidentiality
    0.73
     protection
    0.73
    TRY
    0.73
     executing
    0.72
    Act Density 0.101%

    No Known Activations