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

    Neuronpedia

    INDEX
    Explanations

    references to specific numeric values or identifiers in scientific contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    */),
    -0.76
     >(
    -0.74
     Werth
    -0.74
    ']))
    -0.73
    .”—
    -0.73
    ResumeLayout
    -0.73
    Рис
    -0.72
     ComVisible
    -0.72
     autorytatywna
    -0.72
     McGovern
    -0.72
    POSITIVE LOGITS
    2
    1.44
    nd
    1.28
    0
    1.18
    5
    1.01
    3
    0.98
    4
    0.98
    1
    0.92
    8
    0.83
    6
    0.83
    7
    0.80
    Act Density 1.870%

    No Known Activations