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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating measurement ranges or assessments of agreement

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    ">//
    -0.56
    trades
    -0.52
     itself
    -0.51
     Itself
    -0.50
     unexpected
    -0.49
     nariz
    -0.49
     sendiri
    -0.47
     Woodford
    -0.47
    force
    -0.45
    수
    -0.45
    POSITIVE LOGITS
    enumi
    0.72
    tvguidetime
    0.71
     ivelany
    0.65
    toContain
    0.65
    MessageState
    0.62
    PerformLayout
    0.61
    المناصب
    0.61
    yní
    0.60
    csolódó
    0.60
    CTYPE
    0.59
    Act Density 0.029%

    No Known Activations