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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the presence of multiple entities and activities related to events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    actionDate
    -0.15
    Defense
    -0.15
    URES
    -0.14
     nowrap
    -0.14
     kar
    -0.14
    ilim
    -0.13
     Ñģез
    -0.13
    iro
    -0.13
    ael
    -0.13
    '])?
    -0.13
    POSITIVE LOGITS
    skirts
    0.15
    ê´
    0.15
     specials
    0.14
    idor
    0.14
    foy
    0.14
    린ìĿ´
    0.13
    eload
    0.13
    ojis
    0.13
    omanip
    0.13
    saldo
    0.13
    Act Density 0.005%

    No Known Activations