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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating repetition or redundancy in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aku
    -0.18
    819
    -0.16
    409
    -0.15
    iname
    -0.15
    204
    -0.15
    ĢìĿ´
    -0.14
    217
    -0.14
    culate
    -0.14
    532
    -0.14
    pei
    -0.14
    POSITIVE LOGITS
    uco
    0.22
     Canter
    0.17
    icone
    0.15
    -flex
    0.15
    another
    0.15
    otte
    0.15
    iks
    0.15
    layan
    0.15
    estone
    0.15
    anela
    0.14
    Act Density 0.049%

    No Known Activations