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

    Neuronpedia

    INDEX
    Explanations

    elements related to measurements, analysis, and evaluation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     >=",
    -1.06
    AndEndTag
    -0.92
    ngdoc
    -0.91
    parsedMessage
    -0.89
    NameInMap
    -0.85
    ScopeManager
    -0.82
    setVerticalGroup
    -0.81
    Kariera
    -0.80
    Билгалдахарш
    -0.79
     CURIAM
    -0.79
    POSITIVE LOGITS
    いが
    0.43
     cho
    0.42
    ww
    0.39
    thers
    0.39
     mer
    0.39
     but
    0.39
    S
    0.39
     note
    0.38
    ье
    0.38
    <eos>
    0.38
    Act Density 0.080%

    No Known Activations