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

    Neuronpedia

    INDEX
    Explanations

    financial and economic terms

    oai_token-act-pair · gpt-3.5-turbo

    punctuation, specifically periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     seams
    -0.73
    iquette
    -0.70
     intellig
    -0.64
     Portug
    -0.63
     nearby
    -0.63
     battles
    -0.62
     utilities
    -0.62
     surrogate
    -0.62
     closest
    -0.61
     skirm
    -0.61
    POSITIVE LOGITS
    âĢ¦]
    1.53
    ...]
    1.50
    Pg
    1.31
    emphasis
    1.15
    Footnote
    1.13
    ?]
    1.11
    sic
    1.03
    !]
    1.01
     ].
    1.01
    note
    0.99
    Act Density 0.036%

    No Known Activations