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

    Neuronpedia

    INDEX
    Explanations

    phrases implying conditionality or consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Personensuche
    -1.10
    Билгалдахарш
    -1.04
    awtextra
    -1.02
    -1.01
     estimés
    -1.00
    ThroughAttribute
    -0.98
    __":
    -0.98
    ConstraintMaker
    -0.97
    GEBURTSDATUM
    -0.96
     Савезне
    -0.95
    POSITIVE LOGITS
     the
    0.76
    ,
    0.58
     of
    0.57
     a
    0.57
     our
    0.53
     an
    0.53
     those
    0.52
     like
    0.51
    “
    0.51
     with
    0.51
    Act Density 0.834%

    No Known Activations