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

    Neuronpedia

    INDEX
    Explanations

    expressions related to risks and uncertainties in future projections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ube
    -0.17
    _DECLARE
    -0.15
     ÄIJiá»ĩn
    -0.15
    UBE
    -0.15
    elsea
    -0.14
    reau
    -0.14
    çe
    -0.13
    gun
    -0.13
     Cad
    -0.13
    azi
    -0.13
    POSITIVE LOGITS
     Burr
    0.15
    assic
    0.14
    lius
    0.14
    gens
    0.14
    tainment
    0.14
     reserves
    0.14
     unknown
    0.13
    км
    0.13
    tener
    0.13
    adel
    0.13
    Act Density 0.049%

    No Known Activations