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

    Neuronpedia

    INDEX
    Explanations

    keywords and phrases related to debate structures and formats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    _rom
    -0.15
     докÑĥм
    -0.15
     INTERRUPTION
    -0.15
     огÑĢа
    -0.15
    ICON
    -0.15
    .pp
    -0.14
     Interr
    -0.14
    disp
    -0.14
    .hd
    -0.14
     ëĤĺê°Ģ
    -0.14
    POSITIVE LOGITS
    uem
    0.18
    nect
    0.15
     cl
    0.15
     civilization
    0.15
     Bou
    0.15
    uil
    0.15
     att
    0.14
     Edition
    0.14
    perature
    0.14
     Mason
    0.14
    Act Density 0.347%

    No Known Activations