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

    Neuronpedia

    INDEX
    Explanations

    various item categories and identifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uxxxx
    -0.88
     StringTokenizer
    -0.87
    Autoritní
    -0.83
    featureID
    -0.83
    ImageContext
    -0.83
    Datuak
    -0.82
    FieldBuilder
    -0.82
     незавершена
    -0.81
    LEncoder
    -0.79
    Халык
    -0.78
    POSITIVE LOGITS
     
    0.69
    <bos>
    0.59
     was
    0.56
    '
    0.55
     E
    0.53
     +
    0.51
    ’
    0.50
     &
    0.48
    ?
    0.47
    ;
    0.47
    Act Density 0.658%

    No Known Activations