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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating conditional or hypothetical situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ERING
    -0.15
    inkel
    -0.15
    wick
    -0.15
     åº
    -0.15
    arsi
    -0.14
    erts
    -0.14
    oglobin
    -0.14
    ering
    -0.14
    VED
    -0.13
    Lite
    -0.13
    POSITIVE LOGITS
    ogle
    0.24
    gether
    0.23
     detriment
    0.21
     extent
    0.21
    ils
    0.20
    ying
    0.18
    vert
    0.17
    /from
    0.17
    tes
    0.17
     extents
    0.17
    Act Density 0.314%

    No Known Activations