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

    Neuronpedia

    INDEX
    Explanations

    terms related to application policies and validation processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    %'↵
    -0.24
    __':↵
    -0.23
    '>↵
    -0.22
    /';↵
    -0.21
    !';↵
    -0.20
    :';↵
    -0.20
    ':''
    -0.20
    /'↵↵
    -0.19
    .';↵
    -0.19
    ;'↵
    -0.19
    POSITIVE LOGITS
    ",
    0.68
    ”,
    0.54
     ",
    0.50
    ',
    0.46
    »,
    0.46
    .",
    0.43
    !",
    0.43
    ",↵
    0.43
    ?",
    0.42
    )",
    0.41
    Act Density 0.113%

    No Known Activations