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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating dialogues or speeches

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    âĢĮد
    -0.17
    UNUSED
    -0.17
     ðŁĺī↵↵
    -0.16
    voie
    -0.16
    sled
    -0.15
    chester
    -0.15
    ddy
    -0.15
    ãĤŃãĥ¼
    -0.15
    engeance
    -0.15
    (æľĪ
    -0.15
    POSITIVE LOGITS
     PAC
    0.14
     Herrera
    0.14
    atem
    0.14
    ži
    0.14
    ilos
    0.14
     America
    0.13
     gonna
    0.13
    ãĥįãĥ«
    0.13
     fiss
    0.13
    gon
    0.13
    Act Density 0.004%

    No Known Activations