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

    Neuronpedia

    INDEX
    Explanations

    phrases related to investigative journalism and uncovering hidden information

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    .",
    -0.67
    ",
    -0.67
    !",
    -0.63
    ',
    -0.63
    ':
    -0.62
    ,'
    -0.61
    \",
    -0.60
    %:
    -0.59
    )",
    -0.59
     Folder
    -0.58
    POSITIVE LOGITS
    uously
    0.83
    iously
    0.81
    ingly
    0.69
    ĸļ
    0.68
    Ö¼
    0.68
    uably
    0.67
    bably
    0.66
    aciously
    0.65
     millennia
    0.65
    ously
    0.64
    Act Density 1.158%

    No Known Activations