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

    Neuronpedia

    INDEX
    Explanations

    the concept of "quality" or "attributes of entities."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     SafeMath
    -0.65
    יצוב
    -0.63
     sols
    -0.63
     onCreateView
    -0.61
     gaf
    -0.56
     Isolation
    -0.55
    nyv
    -0.53
    brl
    -0.52
     NSCoder
    -0.52
     Bosco
    -0.51
    POSITIVE LOGITS
    ality
    4.26
    ALITY
    3.04
    alities
    2.92
    uality
    1.45
    nalité
    1.19
    icity
    1.19
    lity
    1.17
    alty
    1.12
    alité
    1.07
    ITY
    1.05
    Act Density 0.119%

    No Known Activations