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

    Neuronpedia

    INDEX
    Explanations

    instances of slashes and backslashes used as separators or indicators

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <blockquote>
    -0.86
     Chees
    -0.79
     Efq
    -0.78
    ภัณฑ์
    -0.73
     raiſ
    -0.73
    *>(
    -0.72
     pleaſure
    -0.72
     pinak
    -0.70
    UIL
    -0.70
     COB
    -0.69
    POSITIVE LOGITS
     /
    1.22
    iwa
    0.99
     Mathis
    0.95
     ApiException
    0.93
     /\
    0.89
    uvre
    0.86
    cektir
    0.85
     /=
    0.85
     Rosenthal
    0.85
    :✨
    0.82
    Act Density 0.125%

    No Known Activations