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

    Neuronpedia

    INDEX
    Explanations

    negative values and mathematical symbols related to statistical or probability models

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    لينكات
    -0.41
    ︎
    -0.39
    s
    -0.37
     Giuliani
    -0.31
     Surely
    -0.31
     Få
    -0.31
     laud
    -0.30
     $[\
    -0.30
    SharedCtor
    -0.30
    Gesture
    -0.30
    POSITIVE LOGITS
     $-
    1.84
    $-
    1.39
     −
    1.38
     (−
    1.27
     (-
    1.22
    −
    1.22
     }-
    1.13
    (−
    1.09
    (-
    1.06
     [-
    1.05
    Act Density 0.276%

    No Known Activations