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

    Neuronpedia

    INDEX
    Explanations

    instances of character interactions and relationships in narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    аÑĢÑĩ
    -0.20
    oto
    -0.16
    raud
    -0.15
    Arc
    -0.14
    bid
    -0.14
    andest
    -0.14
     Xxx
    -0.13
    aur
    -0.13
    mour
    -0.13
    utan
    -0.13
    POSITIVE LOGITS
     vag
    0.16
    uckles
    0.16
    uy
    0.15
    orny
    0.15
    ick
    0.14
     воÑĢ
    0.14
     Ease
    0.14
    ucks
    0.14
    ecom
    0.14
    orns
    0.13
    Act Density 0.081%

    No Known Activations