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

    Neuronpedia

    INDEX
    Explanations

    protocol identifiers related to network communication

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    IntoConstraints
    -0.69
     TestBed
    -0.67
    LabelTagHelper
    -0.64
    :✨
    -0.62
    NameInMap
    -0.59
    yntaxException
    -0.56
    ništvo
    -0.55
    tagHelperRunner
    -0.54
    +#+#
    -0.54
    AutoScaleMode
    -0.53
    POSITIVE LOGITS
    ';
    0.53
    <bos>
    0.51
    ';
    0.51
    '};
    0.51
     ':
    0.47
    carrera
    0.46
     ":
    0.46
    ";
    0.46
    ').
    0.46
     wont
    0.45
    Act Density 0.077%

    No Known Activations