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

    Neuronpedia

    INDEX
    Explanations

    information related to statistical data and numbers in a text

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     „,
    -0.85
     vnd
    -0.84
     mef
    -0.83
     immen
    -0.81
     sappi
    -0.81
     blos
    -0.80
     circon
    -0.79
     socie
    -0.78
     dè
    -0.78
     subtil
    -0.77
    POSITIVE LOGITS
     hardly
    0.60
     barely
    0.59
    siye
    0.58
     limited
    0.57
     thôi
    0.57
     paltry
    0.54
     negligible
    0.54
     otherwise
    0.54
     Otherwise
    0.52
     mostly
    0.52
    Act Density 0.494%

    No Known Activations