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

    Neuronpedia

    INDEX
    Explanations

    numerical codes or sequences

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     impractica
    -0.77
     tolerably
    -0.67
     shenan
    -0.63
     depic
    -0.63
     unspeak
    -0.59
     salutary
    -0.58
     gaily
    -0.58
     unlaw
    -0.58
     intersper
    -0.57
     perusal
    -0.56
    POSITIVE LOGITS
    Tikang
    0.58
     núm
    0.57
     alkoh
    0.56
     Kategor
    0.54
     dras
    0.53
     behar
    0.53
     gmbh
    0.53
     potest
    0.52
     maxime
    0.52
     Fichier
    0.52
    Act Density 0.299%

    No Known Activations