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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and formatting characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Климат
    -0.69
    uanya
    -0.54
    tighet
    -0.54
    χρι
    -0.53
     straips
    -0.52
     sää
    -0.52
    feinander
    -0.51
     ilmo
    -0.51
    benz
    -0.50
     McFarland
    -0.50
    POSITIVE LOGITS
    ########.
    0.86
    antaine
    0.82
    */].
    0.77
    uxxxx
    0.75
    ++]=
    0.74
    ftagPool
    0.73
    !(:
    0.73
    LikeLike
    0.72
    Portale
    0.71
    Portail
    0.70
    Act Density 0.282%

    No Known Activations