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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating significant moments or milestones

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    imits
    -0.17
     pointer
    -0.15
    ulously
    -0.15
    how
    -0.15
    ark
    -0.15
    elight
    -0.15
    -alert
    -0.15
    jÃŃm
    -0.14
    vert
    -0.14
     pointers
    -0.14
    POSITIVE LOGITS
    edly
    0.25
    ill
    0.23
    wise
    0.22
    lessly
    0.21
    aneous
    0.21
     зÑĢениÑı
    0.19
    y
    0.19
    -of
    0.18
    eur
    0.17
    age
    0.16
    Act Density 0.067%

    No Known Activations