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

    Neuronpedia

    INDEX
    Explanations

    references to variables or parameters in mathematical expressions or programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ―――――
    -0.93
     $_"
    -0.91
    wiſe
    -0.88
     Diſ
    -0.84
     ſeveral
    -0.84
     itſelf
    -0.83
     myſelf
    -0.81
     ་་
    -0.81
    .}~\
    -0.80
    neſs
    -0.80
    POSITIVE LOGITS
     q
    1.55
    q
    1.49
     Q
    1.31
    Q
    1.24
    ｑ
    1.08
    paq
    1.01
    Iq
    0.96
     oocytes
    0.96
    kq
    0.92
     Iq
    0.90
    Act Density 0.089%

    No Known Activations