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

    Neuronpedia

    INDEX
    Explanations

    references to specific high-rated words indicating evaluation or emphasis, particularly emphasizing particular concepts or actions

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Negative Logits
    NUMX
    -1.06
     XNUMX
    -0.98
     ciasc
    -0.94
     stället
    -0.85
     whoſe
    -0.84
     ainfi
    -0.82
     särskilt
    -0.75
     plufieurs
    -0.75
     särsk
    -0.75
     |
    -0.73
    POSITIVE LOGITS
     definately
    1.06
     loosing
    0.93
     diatas
    0.90
    に於
    0.90
     alot
    0.86
    Whilst
    0.84
     dependant
    0.81
     Whilst
    0.79
     للمعارف
    0.79
     aprox
    0.79
    Act Density 2.647%

    No Known Activations