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

    Neuronpedia

    INDEX
    Explanations

    end punctuation marks, particularly periods and quotation marks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    amp
    -0.15
    gie
    -0.15
    shops
    -0.15
    lar
    -0.14
    çķĮ
    -0.14
    athers
    -0.14
    és
    -0.14
    urai
    -0.14
    ies
    -0.13
    ties
    -0.13
    POSITIVE LOGITS
    ¦
    0.22
     said
    0.20
    },{"
    0.18
    aly
    0.17
     says
    0.17
     dedim
    0.16
    primir
    0.15
    ATAB
    0.14
    },"
    0.14
     />↵
    0.14
    Act Density 0.193%

    No Known Activations