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

    Neuronpedia

    INDEX
    Explanations

    sections of text that reference dates or timestamps

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    busters
    -0.15
    lad
    -0.15
    urr
    -0.15
    igm
    -0.14
    oris
    -0.14
     habit
    -0.14
    urse
    -0.14
    oding
    -0.14
    ignty
    -0.14
     Habit
    -0.13
    POSITIVE LOGITS
    iola
    0.18
    aho
    0.16
     subrange
    0.16
    ruž
    0.15
    ataire
    0.15
     âĨĶ
    0.15
    arius
    0.15
    .datab
    0.15
    aco
    0.14
    .getLog
    0.14
    Act Density 0.010%

    No Known Activations