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

    Neuronpedia

    INDEX
    Explanations

    expressions of appreciation or positive feedback

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ViewImports
    -0.94
     CreateTagHelper
    -0.91
    __":
    -0.84
     FetchType
    -0.82
    gonic
    -0.82
     /\.(
    -0.79
    TestingModule
    -0.79
    __':
    -0.77
     pinulongan
    -0.76
     للاسماء
    -0.73
    POSITIVE LOGITS
     sekali
    0.47
    Демографія
    0.46
     нравится
    0.46
     version
    0.46
    ksen
    0.44
     demas
    0.42
     creep
    0.41
     nicer
    0.40
     gillar
    0.40
     concept
    0.39
    Act Density 0.153%

    No Known Activations