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

    Neuronpedia

    INDEX
    Explanations

    mathematical symbols and notations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    y
    -1.81
    e
    -1.30
    o
    -1.27
    i
    -1.26
    t
    -1.25
    n
    -1.25
    d
    -1.20
    u
    -1.17
    l
    -1.16
    s
    -1.13
    POSITIVE LOGITS
     myſelf
    1.89
     themſelves
    1.80
     pleaſure
    1.73
     purpoſe
    1.72
     itſelf
    1.72
     Efq
    1.67
    ſelves
    1.66
     reaſon
    1.65
     himſelf
    1.65
     Anſ
    1.65
    Act Density 1.170%

    No Known Activations