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

    Neuronpedia

    INDEX
    Explanations

    references to limitations and uncertainties in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    benh
    -0.16
    igo
    -0.16
    ãĥªãĥ¼ãĤº
    -0.15
    /*č↵
    -0.15
     primer
    -0.15
    ÅĦst
    -0.14
    åĭĻ
    -0.14
    IGO
    -0.14
    elters
    -0.14
     somehow
    -0.14
    POSITIVE LOGITS
     anymore
    0.95
     nữa
    0.57
     lagi
    0.41
     longer
    0.36
    åĨį
    0.32
     again
    0.31
     Longer
    0.28
     artık
    0.27
     دÛĮگر
    0.26
     no
    0.26
    Act Density 0.208%

    No Known Activations