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

    Neuronpedia

    INDEX
    Explanations

    symbols and formatting related to mathematical expressions and matrices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     fact
    -0.59
    cdnjs
    -0.55
    featureID
    -0.55
    multicolumn
    -0.54
     فريبيس
    -0.52
    GNUC
    -0.52
    zsche
    -0.52
    Fuckin
    -0.52
    esgue
    -0.52
     super
    -0.51
    POSITIVE LOGITS
     purpoſe
    0.91
    hdashline
    0.88
     houſe
    0.86
     ſever
    0.84
     vectorielle
    0.80
     Meksiku
    0.80
     uſed
    0.78
     ſeveral
    0.77
     whoſe
    0.77
     ſche
    0.77
    Act Density 0.121%

    No Known Activations