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

    Neuronpedia

    INDEX
    Explanations

    the presence of symbols or punctuation in text

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    OGND
    -0.76
    AddTagHelper
    -0.71
    UseVisualStyle
    -0.64
    ISTICS
    -0.64
    EndProject
    -0.63
     AssemblyTitle
    -0.63
    __':
    -0.62
    runApp
    -0.62
    DockStyle
    -0.61
    __":
    -0.59
    POSITIVE LOGITS
     Majefty
    0.60
     ſche
    0.49
    toim
    0.46
     Minif
    0.46
     IRIS
    0.45
     cune
    0.44
     parry
    0.44
     Deve
    0.43
    hassee
    0.42
     Ministero
    0.42
    Act Density 0.004%

    No Known Activations