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

    Neuronpedia

    INDEX
    Explanations

    escaped characters or sequences in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     يتيمه
    -0.86
     Kości
    -0.81
    geocode
    -0.78
     berg
    -0.77
    Eres
    -0.74
    дь
    -0.73
    cuss
    -0.73
    osc
    -0.71
     Goose
    -0.70
     BorderRadius
    -0.69
    POSITIVE LOGITS
    "\
    1.11
    :\
    1.10
    '\
    1.09
    >\
    1.07
    ("\
    1.06
    <<"\
    1.05
    ('\
    1.03
    ?\
    1.01
     "\
    1.00
     "..\..\..\
    0.99
    Act Density 0.200%

    No Known Activations