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

    Neuronpedia

    INDEX
    Explanations

    phrases related to physical acts of aggression or force

    oai_token-act-pair · gpt-3.5-turbo

    references to physical violence and conflict-related actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    interstitial
    -0.81
    culosis
    -0.70
    folio
    -0.68
    occupied
    -0.65
    worm
    -0.65
    ears
    -0.64
    bee
    -0.64
    JO
    -0.62
    artist
    -0.62
     ASAP
    -0.62
    POSITIVE LOGITS
     punches
    1.30
     deliberations
    0.98
    arnaev
    0.81
    ;;;;;;;;
    0.71
    ãĥĥãĥī
    0.70
    =-=-=-=-=-=-=-=-
    0.70
    ogun
    0.68
     sidx
    0.68
     Rus
    0.67
    åij
    0.67
    Act Density 0.001%

    No Known Activations