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

    Neuronpedia

    INDEX
    Explanations

    terminology related to mathematical proofs and concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     itſelf
    -1.80
    BibitemShut
    -1.80
     ་་
    -1.77
     myſelf
    -1.63
    >\<^
    -1.55
     Theſe
    -1.52
     iſt
    -1.48
     ―――――
    -1.47
     Anſ
    -1.46
    ſelf
    -1.45
    POSITIVE LOGITS
    r
    1.10
    P
    1.01
    p
    0.97
    m
    0.97
    b
    0.97
    l
    0.96
    S
    0.95
    R
    0.95
    op
    0.95
    Z
    0.93
    Act Density 1.710%

    No Known Activations