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

    Neuronpedia

    INDEX
    Explanations

    references to pauses or separations in lists

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     iſt
    -1.19
     faſt
    -1.15
    ſelf
    -1.12
    leſs
    -1.12
     itſelf
    -1.08
     ―――――
    -1.06
     ſche
    -1.04
    eſt
    -0.99
     verſ
    -0.98
     Anſ
    -0.97
    POSITIVE LOGITS
    ,
    2.09
    ，
    1.59
    ),
    1.55
    .,
    1.50
    (),
    1.47
    ،
    1.45
     ,
    1.42
    },
    1.37
    ],
    1.36
    、
    1.35
    Act Density 2.760%

    No Known Activations