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

    Neuronpedia

    INDEX
    Explanations

    elements related to instruction or guidance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    addock
    -0.15
    eva
    -0.15
     addCriterion
    -0.15
    ebo
    -0.15
    .appspot
    -0.15
    ake
    -0.14
    idla
    -0.14
    direct
    -0.14
     bargain
    -0.14
    itur
    -0.14
    POSITIVE LOGITS
    trap
    0.16
    ancell
    0.15
    asic
    0.15
    akit
    0.14
    ograd
    0.14
    177
    0.14
    ancel
    0.14
    aska
    0.13
    ÙĬÙĦÙħ
    0.13
    133
    0.13
    Act Density 0.004%

    No Known Activations