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

    Neuronpedia

    INDEX
    Explanations

    conditional phrases indicating hypothetical situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eming
    -0.15
    isse
    -0.15
    elik
    -0.14
    aticon
    -0.14
    uen
    -0.14
    £¼
    -0.14
    Äĥm
    -0.14
    acin
    -0.14
     paci
    -0.14
    allest
    -0.14
    POSITIVE LOGITS
     Nez
    0.14
    ques
    0.14
     sm
    0.13
    ëī´
    0.13
     Sm
    0.13
    .comm
    0.13
    omm
    0.13
    Pairs
    0.13
    oya
    0.13
     cl
    0.13
    Act Density 0.133%

    No Known Activations