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

    Neuronpedia

    INDEX
    Explanations

    technical details and guidelines in a text, potentially related to software development or hardware specifications

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    MET
    -0.92
    gee
    -0.85
    english
    -0.85
    MON
    -0.85
    cause
    -0.84
    ctors
    -0.84
    emale
    -0.83
    lde
    -0.82
    tty
    -0.81
    gram
    -0.80
    POSITIVE LOGITS
     onwards
    1.09
    points
    1.08
     onward
    1.03
    abouts
    1.01
    manship
    1.00
    ebin
    1.00
    point
    0.97
    SPONSORED
    0.93
    Ħ¢
    0.92
     iteration
    0.87
    Act Density 0.575%

    No Known Activations