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

    Neuronpedia

    INDEX
    Explanations

    LaTeX formatting elements, particularly those used for mathematical expressions and equations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    y
    -1.29
    l
    -0.95
    c
    -0.94
    z
    -0.93
    i
    -0.93
    x
    -0.92
    n
    -0.91
    h
    -0.91
    -
    -0.88
    p
    -0.87
    POSITIVE LOGITS
     themſelves
    1.70
     myſelf
    1.66
     Efq
    1.66
     pleaſure
    1.60
    })*/
    1.55
     purpoſe
    1.49
     Anſ
    1.48
     Theſe
    1.48
    ſelves
    1.47
     uſed
    1.46
    Act Density 0.932%

    No Known Activations