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

    Neuronpedia

    INDEX
    Explanations

    words and phrases indicating actions, conditions, or relationships in narrative contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ernes
    -0.15
    adius
    -0.15
    missible
    -0.14
    composition
    -0.14
    associ
    -0.14
    ideshow
    -0.13
    ickerView
    -0.13
    ẽ
    -0.13
    endoza
    -0.13
    agra
    -0.13
    POSITIVE LOGITS
    daf
    0.17
    ris
    0.15
     èī
    0.15
    ulis
    0.15
    sb
    0.14
    enis
    0.14
    ึà¸ĩ
    0.14
    acher
    0.14
    ãĥ¬ãĥ³
    0.14
    zan
    0.13
    Act Density 0.006%

    No Known Activations