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

    Neuronpedia

    INDEX
    Explanations

    words related to locations and positions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    whom
    -0.85
    whose
    -0.71
     whom
    -0.67
     whose
    -0.66
    Whom
    -0.62
    Whose
    -0.59
     которого
    -0.58
     którego
    -0.57
     Whose
    -0.54
     cuja
    -0.54
    POSITIVE LOGITS
    rungsseite
    0.79
     disambiguazione
    0.78
     wh
    0.69
     الحره
    0.64
    pecabe
    0.63
     typelib
    0.62
     <<<<<<<<<<<<<<
    0.60
     فريبيس
    0.57
    ſammen
    0.56
     kasarigan
    0.56
    Act Density 0.375%

    No Known Activations