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

    Neuronpedia

    INDEX
    Explanations

    the term "latter" and its variations, indicating comparisons or contrasts in discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ernen
    -0.16
    rå
    -0.15
    nict
    -0.14
    vre
    -0.14
    ying
    -0.14
    uese
    -0.14
    اÙĨÙĩ
    -0.13
    ibraltar
    -0.13
    dal
    -0.13
    ÅĤ
    -0.13
    POSITIVE LOGITS
    most
    0.31
    mentioned
    0.23
    -most
    0.20
    -day
    0.20
     beiden
    0.19
     mentioned
    0.19
     category
    0.17
    -described
    0.17
    lain
    0.17
     two
    0.16
    Act Density 0.036%

    No Known Activations