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

    Neuronpedia

    INDEX
    Explanations

    declarative statements or assertions with strong opinions

    oai_token-act-pair · gpt-3.5-turbo

    various sentence endings or punctuation marks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ',"
    -0.67
    !'"
    -0.64
    atility
    -0.57
     Cup
    -0.56
    inguishable
    -0.55
    Thumbnail
    -0.54
    ,'"
    -0.54
    '."
    -0.53
    owan
    -0.53
     teammate
    -0.52
    POSITIVE LOGITS
    ↵Âł
    1.38
     Âł
    1.35
     ³³
    1.30
     Âł Âł
    1.29
    ³³
    1.25
     ]
    1.06
    Âł
    1.05
     )
    1.02
     ):
    1.02
     )]
    0.99
    Act Density 0.477%

    No Known Activations