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

    Neuronpedia

    INDEX
    Explanations

    terms related to utility and probability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Bevan
    -0.81
    HttpPost
    -0.73
    Portale
    -0.73
    tagext
    -0.70
     Anhäng
    -0.70
    en
    -0.68
    got
    -0.67
     enfans
    -0.67
     ARRAY
    -0.67
    EN
    -0.66
    POSITIVE LOGITS
    Utilities
    1.02
     disponibilités
    0.89
     estekak
    0.88
    utilities
    0.87
    QMetaType
    0.84
    texttt
    0.79
    hematical
    0.79
    cological
    0.77
    Примечания
    0.76
    neous
    0.75
    Act Density 0.082%

    No Known Activations