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

    Neuronpedia

    INDEX
    Explanations

    names of notable characters and actors in television series

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    stab
    -0.16
     Manufact
    -0.15
     Burns
    -0.15
     Heal
    -0.15
    els
    -0.14
    adil
    -0.14
    he
    -0.14
    _tm
    -0.14
     worldview
    -0.14
     Lap
    -0.14
    POSITIVE LOGITS
    hoff
    0.17
    ouns
    0.17
    饰
    0.17
     annonces
    0.15
    _compat
    0.15
     ham
    0.14
    quip
    0.14
    飾
    0.14
    _DROP
    0.13
    ovnÃŃ
    0.13
    Act Density 0.064%

    No Known Activations