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

    Neuronpedia

    INDEX
    Explanations

    codes or technical terms related to software or programming

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    ï¸
    -0.89
    PDATE
    -0.87
    ipel
    -0.86
    vic
    -0.84
    iannopoulos
    -0.83
    ħĭ
    -0.82
    Äĩ
    -0.81
    querque
    -0.81
    Ļ½
    -0.81
    ccording
    -0.78
    POSITIVE LOGITS
    576
    1.16
    erences
    0.88
    000
    0.83
    arching
    0.78
    iversary
    0.77
    phrine
    0.77
     commandments
    0.77
    ockets
    0.76
    rolling
    0.76
     refres
    0.76
    Act Density 13.545%

    No Known Activations