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

    Neuronpedia

    INDEX
    Explanations

    terms that indicate reasons or explanations

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     words
    -0.48
     Fair
    -0.45
     A
    -0.45
     fly
    -0.45
    pios
    -0.43
     word
    -0.42
     Throwable
    -0.42
    neri
    -0.42
     Mit
    -0.41
     a
    -0.41
    POSITIVE LOGITS
    SourceChecksum
    0.85
    expandindo
    0.74
     Cæsar
    0.73
     $_"
    0.70
     myſelf
    0.70
     Efq
    0.68
    ngdoc
    0.68
     Shakspeare
    0.67
     Majefty
    0.67
    AsUp
    0.62
    Act Density 0.023%

    No Known Activations