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

    Neuronpedia

    INDEX
    Explanations

    statements about the predictability and representativeness of study results

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    principalColumn
    -0.84
    -0.79
    uxxxx
    -0.71
    oredCriteria
    -0.65
    تقاوى
    -0.64
     افتراض
    -0.63
    GOTREF
    -0.63
    FormTagHelper
    -0.63
     Вікіпе
    -0.60
    fjspx
    -0.59
    POSITIVE LOGITS
    rédients
    0.47
    Actual
    0.45
    âmetros
    0.44
    mockito
    0.43
    δας
    0.42
     behaviour
    0.42
     extrapolation
    0.42
     Pickles
    0.42
    จริง
    0.42
    [],
    0.41
    Act Density 0.121%

    No Known Activations