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

    Neuronpedia

    INDEX
    Explanations

    code-like structures, particularly related to mathematical or logical functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .
    -0.51
    ".
    -0.42
    '.
    -0.41
    !
    -0.39
    <eos>
    -0.38
    ').
    -0.38
     Res
    -0.37
     :
    -0.37
    T
    -0.36
    Res
    -0.36
    POSITIVE LOGITS
     חיצוניים
    1.02
     autorytatywna
    0.97
     שוליים
    0.92
     nahilalakip
    0.84
    tvguidetime
    0.81
     Geſch
    0.79
     Geiſt
    0.75
     kasarigan
    0.72
    StructEnd
    0.72
     Taktlose
    0.71
    Act Density 0.666%

    No Known Activations