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

    Neuronpedia

    INDEX
    Explanations

    URLs and web addresses

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     myſelf
    -1.01
     itſelf
    -0.90
     Jefus
    -0.88
     himſelf
    -0.87
    Geplaatst
    -0.83
     quæ
    -0.82
     AttributeSet
    -0.81
     whoſe
    -0.81
     themſelves
    -0.79
     reaſon
    -0.78
    POSITIVE LOGITS
     cell
    0.53
    filepath
    0.49
     برو
    0.47
    Figs
    0.45
    bulo
    0.45
     xo
    0.45
     might
    0.45
    ESTRA
    0.45
    iland
    0.44
    strando
    0.44
    Act Density 0.006%

    No Known Activations