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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, particularly quotation marks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    İstinadlar
    -0.94
     “
    -0.83
    ]=="
    -0.82
    DDG
    -0.76
    __.
    -0.74
    olph
    -0.73
    ://"
    -0.73
     Maynard
    -0.73
     cortina
    -0.72
    ."/
    -0.71
    POSITIVE LOGITS
     («
    1.23
    ««
    1.20
    .«
    1.20
    ,»
    1.16
    )»
    1.15
    ?«
    1.14
    «
    1.12
    ?»
    1.11
     «
    1.06
    !«
    1.04
    Act Density 0.025%

    No Known Activations