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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate instructional or procedural content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bris
    -0.16
    кав
    -0.15
    ulus
    -0.15
    ãĥŃãĥ¼
    -0.14
     кад
    -0.14
    enus
    -0.14
    arsi
    -0.14
    جا
    -0.13
    gens
    -0.13
    uat
    -0.13
    POSITIVE LOGITS
    oda
    0.16
     further
    0.16
    915
    0.15
    897
    0.14
     weiter
    0.14
    äft
    0.14
    istrovstvÃŃ
    0.14
     Friedman
    0.14
     Moran
    0.13
    ëł
    0.13
    Act Density 0.101%

    No Known Activations