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

    Neuronpedia

    INDEX
    Explanations

    sequences of numeric values and their associations in a structured format

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    leski
    -0.59
     enfans
    -0.58
    릉
    -0.58
     ':'
    -0.57
    utie
    -0.57
    ThemeOverlay
    -0.56
     msg
    -0.55
    RETT
    -0.55
    tigma
    -0.55
     ordini
    -0.53
    POSITIVE LOGITS
     bezeichneter
    0.77
    :✨
    0.73
    abestanden
    0.65
    évaluateur
    0.64
    setVerticalGroup
    0.63
    ScopeManager
    0.59
    ">//
    0.58
     للمعارف
    0.56
     lenker
    0.56
    ArrowToggle
    0.56
    Act Density 0.249%

    No Known Activations