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

    Neuronpedia

    INDEX
    Explanations

    references to collective human experiences and shared struggles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     مشين
    -1.08
    parsedMessage
    -0.97
     للاسماء
    -0.89
    CloseOperation
    -0.88
     }}$}
    -0.87
    SharedDtor
    -0.85
     <<<<<<<<<<<<<<
    -0.85
     صوتيه
    -0.83
    ]$}
    -0.82
    rungsseite
    -0.80
    POSITIVE LOGITS
     Everyone
    0.75
     everyone
    0.74
    Everyone
    0.72
     EVERYONE
    0.72
    everyone
    0.70
     everybody
    0.69
    Everybody
    0.68
     Everybody
    0.65
    everybody
    0.60
     iedereen
    0.55
    Act Density 0.324%

    No Known Activations