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

    Neuronpedia

    INDEX
    Explanations

    instances of aggressive or unusual behavior in a narrative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    amburger
    -0.19
    locker
    -0.15
    ffa
    -0.15
     ais
    -0.14
     underground
    -0.14
    ç¹ģ
    -0.14
    rows
    -0.13
    loat
    -0.13
     Funeral
    -0.13
    iferay
    -0.13
    POSITIVE LOGITS
     door
    0.28
     Door
    0.25
    _door
    0.24
    Door
    0.23
    éŨ
    0.20
     inside
    0.20
    -door
    0.20
    door
    0.20
     knock
    0.19
    inside
    0.19
    Act Density 0.098%

    No Known Activations