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

    Neuronpedia

    INDEX
    Explanations

    numerical values and measurements

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     position
    -0.52
     per
    -0.48
    fährt
    -0.48
     or
    -0.48
     as
    -0.48
     positions
    -0.47
    PickerController
    -0.47
     "
    -0.46
     program
    -0.46
     form
    -0.45
    POSITIVE LOGITS
     myſelf
    0.92
     Efq
    0.89
     незавершена
    0.88
     itſelf
    0.86
     Majefty
    0.81
     againſt
    0.80
     nakalista
    0.80
    EndProject
    0.80
     Shakspeare
    0.77
    RenderAtEndOf
    0.77
    Act Density 0.041%

    No Known Activations