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

    Neuronpedia

    INDEX
    Explanations

    underscore-prefixed identifiers, indicating coding conventions or variable names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AddTagHelper
    -0.92
    <bos>
    -0.85
    LookAnd
    -0.82
    SequentialGroup
    -0.82
     Italijanski
    -0.82
     Chwiliwch
    -0.81
     ſta
    -0.79
     ivelany
    -0.78
     שוליים
    -0.77
     ſol
    -0.77
    POSITIVE LOGITS
    /
    0.36
    ]*
    0.36
    \_
    0.35
    _${
    0.32
    ][
    0.32
    之
    0.31
     aka
    0.31
    ฯ
    0.31
    +"_
    0.31
    ]['
    0.31
    Act Density 0.550%

    No Known Activations