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

    Neuronpedia

    INDEX
    Explanations

    phrases related to epic battles or confrontations

    oai_token-act-pair · gpt-3.5-turbo

    end punctuation marks in sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    abouts
    -0.76
     unpop
    -0.73
    uly
    -0.73
     unprotected
    -0.72
     inactive
    -0.70
     aborted
    -0.68
    lier
    -0.67
     footing
    -0.67
     contraction
    -0.67
     monop
    -0.66
    POSITIVE LOGITS
     Additionally
    1.18
     Featuring
    1.11
     Along
    1.04
     Meanwhile
    1.04
     Through
    1.02
     Each
    0.99
     Their
    0.99
     Throughout
    0.98
     Ultimately
    0.98
     Unfortunately
    0.97
    Act Density 0.809%

    No Known Activations