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

    Neuronpedia

    INDEX
    Explanations

    instances of dashes that indicate transitions or breaks in narrative

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    #
    -0.18
    ansi
    -0.16
    æĭ¬
    -0.15
    ypsy
    -0.15
    -bs
    -0.15
    anela
    -0.14
    zsche
    -0.14
    наÑĩала
    -0.14
    trx
    -0.14
    jem
    -0.14
    POSITIVE LOGITS
    elan
    0.18
     st
    0.17
     Dennis
    0.16
    ,
    0.16
    237
    0.16
    .
    0.15
     Pessoa
    0.14
    sert
    0.14
     Vital
    0.14
    ite
    0.14
    Act Density 0.000%

    No Known Activations