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

    Neuronpedia

    INDEX
    Explanations

    references to prior studies, methods, or statements within a discussion

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     purpoſe
    -0.98
     pleaſure
    -0.95
     Majefty
    -0.91
    ंदीखरीदारी
    -0.84
     myſelf
    -0.84
     Anſ
    -0.83
     fevere
    -0.81
     ſeveral
    -0.81
     greateſt
    -0.80
     ſever
    -0.78
    POSITIVE LOGITS
    prefixer
    0.56
    ÊN
    0.51
     Meksiku
    0.47
    Cancelable
    0.46
     Heads
    0.45
    xAxis
    0.45
     referrerpolicy
    0.45
     Pr
    0.44
    r
    0.44
    XmlRootElement
    0.44
    Act Density 0.011%

    No Known Activations