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

    Neuronpedia

    INDEX
    Explanations

    numerical values or codes mixed with text

    oai_token-act-pair · gpt-3.5-turbo

    specific nouns, particularly those that represent various classifications or categories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    kus
    -0.77
    ovie
    -0.68
     Tanz
    -0.67
     Crescent
    -0.65
    EH
    -0.63
     entreprene
    -0.62
    ndra
    -0.62
    uben
    -0.62
    Laun
    -0.60
     Hoy
    -0.60
    POSITIVE LOGITS
     mismatch
    1.00
     notation
    0.99
     calculation
    0.96
     codes
    0.92
    checks
    0.91
    codes
    0.89
     dictate
    0.88
     requirement
    0.88
    checked
    0.87
     requirements
    0.86
    Act Density 0.400%

    No Known Activations