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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing conditionality and potential outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ucu
    -0.20
    anship
    -0.17
    infeld
    -0.15
    udu
    -0.15
    zan
    -0.15
    uzey
    -0.14
    amburger
    -0.14
    avis
    -0.14
    amil
    -0.14
    _OC
    -0.13
    POSITIVE LOGITS
    izen
    0.16
    czy
    0.15
    Flash
    0.15
    flash
    0.15
    loy
    0.14
     counting
    0.14
    ké
    0.14
    uggest
    0.13
    aupt
    0.13
     necessarily
    0.13
    Act Density 0.097%

    No Known Activations