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

    Neuronpedia

    INDEX
    Explanations

    special characters within code snippets

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    handsome
    -0.47
    Obsah
    -0.45
     rumbling
    -0.45
    Vlast
    -0.44
    Díky
    -0.44
    Polen
    -0.43
    Když
    -0.43
     Nowak
    -0.43
     reggae
    -0.43
     horned
    -0.43
    POSITIVE LOGITS
    ">*
    0.83
     Ottobre
    0.78
    ('*
    0.77
     *}
    0.77
     *
    0.77
     Settembre
    0.76
     germain
    0.75
    //*
    0.73
    {*
    0.73
    vaila
    0.72
    Act Density 0.093%

    No Known Activations