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

    Neuronpedia

    INDEX
    Explanations

    phrases related to making decisions or taking actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    avy
    -0.19
    alt
    -0.16
     Baltic
    -0.16
     Balt
    -0.15
    door
    -0.15
    amer
    -0.15
    oll
    -0.15
    atio
    -0.14
    adel
    -0.14
    ads
    -0.14
    POSITIVE LOGITS
    forme
    0.18
    :async
    0.17
    [now
    0.16
    folio
    0.16
    esson
    0.16
    веÑī
    0.15
    .getMinutes
    0.15
    .rdf
    0.15
    .gdx
    0.15
    -urlencoded
    0.15
    Act Density 0.175%

    No Known Activations