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

    Neuronpedia

    INDEX
    Explanations

    references to numerical data or weak links

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     to
    -0.47
     is
    -0.45
    .
    -0.42
    ServletException
    -0.42
     by
    -0.42
    boj
    -0.42
     for
    -0.42
     I
    -0.41
     up
    -0.41
     has
    -0.41
    POSITIVE LOGITS
    DockStyle
    0.87
    存于互联网档案馆
    0.86
     ་་
    0.85
     ―――――
    0.82
    ⓧ
    0.77
     Anſ
    0.76
     дописавши
    0.76
     Signalez
    0.76
    ^(@)
    0.76
     Majefty
    0.75
    Act Density 0.637%

    No Known Activations