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

    Neuronpedia

    INDEX
    Explanations

    transitional phrases and markers that indicate sequence or time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    LEGRO
    -0.16
    hausen
    -0.16
    eroon
    -0.16
    ollo
    -0.15
    oton
    -0.15
    elial
    -0.15
    iete
    -0.15
    erno
    -0.15
    ̣c
    -0.14
    ughter
    -0.14
    POSITIVE LOGITS
    ìĤ
    0.16
    beg
    0.15
     beg
    0.15
    arge
    0.15
    zon
    0.15
    branch
    0.14
    ioned
    0.14
     McCoy
    0.14
     {}.
    0.14
    éŀ
    0.14
    Act Density 0.403%

    No Known Activations