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

    Neuronpedia

    INDEX
    Explanations

    references to workplace dynamics and allegations of misconduct

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    SourceChecksum
    -0.60
     NSCoder
    -0.59
     ویکی‌پدیا
    -0.59
    :✨
    -0.59
     confidentialité
    -0.57
    principalColumn
    -0.57
     GetYourGuide
    -0.56
    akse
    -0.54
    arraycopy
    -0.54
    клопе
    -0.54
    POSITIVE LOGITS
    Приятного
    0.63
    enumi
    0.56
    — 
    0.55
    raszam
    0.53
    MLLoader
    0.53
    ucas
    0.52
    〢
    0.52
    Xna
    0.51
    raszamy
    0.50
     Dage
    0.50
    Act Density 0.036%

    No Known Activations