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

    Neuronpedia

    INDEX
    Explanations

    references to crime and criminal activity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ointment
    -0.18
    tle
    -0.17
    tems
    -0.17
    mund
    -0.16
    arian
    -0.15
    nev
    -0.15
    rais
    -0.15
    stood
    -0.15
    tlement
    -0.14
    undry
    -0.14
    POSITIVE LOGITS
     Scene
    0.19
     spree
    0.18
     scene
    0.17
    ully
    0.16
     committed
    0.16
    olvers
    0.16
    cene
    0.16
     against
    0.16
    ythe
    0.15
     scenes
    0.15
    Act Density 0.018%

    No Known Activations