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

    Neuronpedia

    INDEX
    Explanations

    actions involving physical force or violence

    oai_token-act-pair · gpt-3.5-turbo

    actions involving physical aggression or control

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     unemploy
    -0.74
     specialization
    -0.73
    ontent
    -0.72
     specialize
    -0.69
     Trib
    -0.68
     listings
    -0.65
    ansk
    -0.65
     1600
    -0.65
     inval
    -0.64
     Blackburn
    -0.64
    POSITIVE LOGITS
    stretched
    1.20
     clasp
    1.12
     waist
    1.12
     hug
    1.11
     knees
    1.10
     crotch
    1.05
     hugged
    1.03
     gently
    1.03
     zipper
    1.03
     hips
    1.03
    Act Density 0.660%

    No Known Activations