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

    Neuronpedia

    INDEX
    Explanations

    names of individuals and organizations on social media

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns and names associated with people and organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     metic
    -1.00
    aditional
    -0.98
     tremend
    -0.94
     eleph
    -0.92
     practition
    -0.92
     mathemat
    -0.87
    ccording
    -0.87
    Ĝ
    -0.86
    ą
    -0.86
    ě
    -0.86
    POSITIVE LOGITS
     (@
    1.94
    ðŁ
    1.14
     @
    1.07
     ðŁ
    1.05
    ($
    1.02
    (&
    1.00
    ®
    0.97
    ðŁij
    0.96
    @
    0.95
    âĿ
    0.94
    Act Density 0.013%

    No Known Activations