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

    Neuronpedia

    INDEX
    Explanations

    descriptions of architectural features and notable locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     célib
    -0.19
     escorte
    -0.17
    erva
    -0.17
     rencont
    -0.16
     Mash
    -0.15
     prostitu
    -0.15
    logg
    -0.14
    ghan
    -0.14
    duk
    -0.14
     Jub
    -0.14
    POSITIVE LOGITS
     France
    0.74
     French
    0.68
    France
    0.67
     Paris
    0.64
    French
    0.63
     french
    0.60
    Paris
    0.58
    æ³ķåĽ½
    0.58
     france
    0.58
     ÑĦÑĢанÑĨÑĥз
    0.54
    Act Density 0.666%

    No Known Activations