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

    Neuronpedia

    INDEX
    Explanations

    words related to actions or commands in a contextual setting

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     CreateTagHelper
    -0.78
     anzu
    -0.74
    +#+#
    -0.73
     @"/
    -0.72
     مرئيه
    -0.70
    Tikang
    -0.69
     Coyle
    -0.69
    CodeAttribute
    -0.68
    ################
    -0.68
    édrale
    -0.67
    POSITIVE LOGITS
    ¯
    1.20
     ¯
    1.05
     PyObject
    0.86
     LMS
    0.85
     Shank
    0.70
    ISTRATION
    0.69
    LMS
    0.69
     Sheng
    0.66
     ADMINISTRATION
    0.66
     öss
    0.65
    Act Density 0.000%

    No Known Activations