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

    Neuronpedia

    INDEX
    Explanations

    numerical data and references that indicate specific values in a technical or scientific context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anca
    -0.17
    145
    -0.16
    147
    -0.16
    alez
    -0.16
    æŁĶ
    -0.15
    159
    -0.15
    42
    -0.15
    lyph
    -0.14
    144
    -0.14
    54
    -0.14
    POSITIVE LOGITS
    346
    0.47
    356
    0.46
    360
    0.45
    350
    0.45
    355
    0.44
    340
    0.44
    353
    0.44
    348
    0.44
    347
    0.44
    342
    0.44
    Act Density 0.062%

    No Known Activations