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

    Neuronpedia

    INDEX
    Explanations

    patterns of negation or rejection in a context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    room
    -0.17
    ionic
    -0.17
    une
    -0.17
    alo
    -0.16
    iner
    -0.16
    avan
    -0.15
    agn
    -0.15
    robe
    -0.15
    ui
    -0.15
    obj
    -0.15
    POSITIVE LOGITS
    Over
    0.19
    Part
    0.18
    Us
    0.18
    Æł
    0.18
    Event
    0.17
    Rel
    0.17
    Plus
    0.17
    Pre
    0.17
    aeda
    0.16
    idUser
    0.16
    Act Density 0.110%

    No Known Activations