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

    Neuronpedia

    INDEX
    Explanations

    references to measurement units or specifications

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     tø
    -0.64
     Calli
    -0.61
     GOS
    -0.61
    -0.61
    ↠
    -0.60
     Dari
    -0.60
    slash
    -0.60
     SGS
    -0.60
     Yous
    -0.60
    numRows
    -0.59
    POSITIVE LOGITS
     units
    1.61
     unit
    1.49
     Units
    1.49
    units
    1.47
    unit
    1.41
     UNIT
    1.41
     Unit
    1.40
    Units
    1.34
    Unit
    1.33
    UNIT
    1.32
    Act Density 0.054%

    No Known Activations