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

    Neuronpedia

    INDEX
    Explanations

    the word "Derby" at different activations

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Derby and individuals related to it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    itar
    -0.95
    ities
    -0.93
    ITIES
    -0.90
    ité
    -0.87
    itary
    -0.86
    ropri
    -0.86
    ified
    -0.84
    uador
    -0.84
    itol
    -0.81
    itatively
    -0.80
    POSITIVE LOGITS
    lli
    0.86
     Devils
    0.78
     detector
    0.74
    Fax
    0.73
    DoS
    0.73
    lla
    0.71
     Derby
    0.69
     sting
    0.68
     Gibbs
    0.67
     detectors
    0.67
    Act Density 0.042%

    No Known Activations