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

    Neuronpedia

    INDEX
    Explanations

    references to global concepts or issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     défend
    -0.94
     rencontr
    -0.82
     étoit
    -0.74
     vestiti
    -0.72
     CreateTagHelper
    -0.72
     Nymp
    -0.70
     RIAA
    -0.69
     doigts
    -0.68
     peruana
    -0.68
     PyQt
    -0.67
    POSITIVE LOGITS
     global
    1.36
     Global
    1.33
     GLOBAL
    1.25
    GLOBAL
    1.22
    Global
    1.07
    lobal
    1.06
    globals
    1.03
     globales
    0.99
    global
    0.96
     globals
    0.96
    Act Density 0.043%

    No Known Activations