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

    Neuronpedia

    INDEX
    Explanations

    references to self-identification or self-referencing phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     للمعارف
    -0.69
    djangoproject
    -0.68
    PageContext
    -0.67
     Marien
    -0.66
    miro
    -0.63
     MIME
    -0.60
    stuffs
    -0.59
     Moray
    -0.59
     ergo
    -0.57
    Pesquisa
    -0.57
    POSITIVE LOGITS
     call
    1.65
     calling
    1.62
     CALL
    1.59
     Calling
    1.55
     calls
    1.55
    calling
    1.48
     Call
    1.45
     Calls
    1.45
     Called
    1.43
    Calling
    1.42
    Act Density 0.131%

    No Known Activations