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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and probabilities related to arrangements and selections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ripper
    -0.15
    iffin
    -0.15
    ìĶ
    -0.14
    _NEG
    -0.14
    olvers
    -0.14
    ither
    -0.14
    idine
    -0.14
     ÙĨب
    -0.14
     Arrow
    -0.13
     Bark
    -0.13
    POSITIVE LOGITS
     bin
    0.31
     comb
    0.29
    bin
    0.28
     Bin
    0.28
     factorial
    0.28
    .bin
    0.25
     ways
    0.24
     perm
    0.24
    Bin
    0.24
    (bin
    0.23
    Act Density 0.092%

    No Known Activations