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

    Neuronpedia

    INDEX
    Explanations

    mentions of software or related terms

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "software."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    agher
    -0.94
    lain
    -0.84
    uating
    -0.79
    naire
    -0.73
    azon
    -0.71
    onna
    -0.71
     Pound
    -0.70
    bow
    -0.69
    Ze
    -0.69
    erent
    -0.69
    POSITIVE LOGITS
    works
    0.86
     engineering
    0.83
     piracy
    0.82
     RAID
    0.81
     Engineer
    0.81
     engineer
    0.80
    kit
    0.79
     patents
    0.79
    bytes
    0.78
    ĨĴ
    0.77
    Act Density 0.015%

    No Known Activations