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

    Neuronpedia

    INDEX
    Explanations

    conditional phrasing that presents alternatives or choices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    landa
    -0.17
    á»ijc
    -0.16
    even
    -0.15
    707
    -0.14
    ADOR
    -0.14
    atsby
    -0.14
    IQUE
    -0.14
    hear
    -0.14
    occasion
    -0.14
    Ĩ
    -0.13
    POSITIVE LOGITS
     either
    0.40
     Either
    0.38
    either
    0.33
     EITHER
    0.32
    Either
    0.32
     либо
    0.32
     else
    0.27
     soit
    0.21
     elif
    0.19
    ê±°ëĤĺ
    0.19
    Act Density 0.109%

    No Known Activations