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

    Neuronpedia

    INDEX
    Explanations

    the initial token or identifiers indicating the start of a text or data sequence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    StructEnd
    -0.78
    AndEndTag
    -0.64
    urlencoded
    -0.56
    penup
    -0.52
    MessageOf
    -0.52
    ViewFeatures
    -0.51
     sahiptir
    -0.50
     mergeFrom
    -0.49
     שוליים
    -0.48
     ..."
    -0.48
    POSITIVE LOGITS
     anſ
    0.61
     reaſon
    0.61
     raiſ
    0.60
     RoutedEventArgs
    0.58
     uſed
    0.58
     ſtate
    0.56
     ſur
    0.55
     MonoBehaviour
    0.55
     myſelf
    0.55
     demurrer
    0.54
    Act Density 0.015%

    No Known Activations