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

    Neuronpedia

    INDEX
    Explanations

    phrases related to physical injuries

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals who are injured or hurt

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ordan
    -0.84
    ramid
    -0.82
    ãĥİ
    -0.71
    ellar
    -0.69
    oras
    -0.69
    UTH
    -0.69
    é¾
    -0.68
    ODE
    -0.67
    SpaceEngineers
    -0.67
     patented
    -0.66
    POSITIVE LOGITS
    stre
    0.97
     inflicted
    0.96
     wounds
    0.95
     wounding
    0.89
     wounded
    0.86
    bane
    0.85
    gun
    0.83
    lyak
    0.80
    lehem
    0.79
    killers
    0.76
    Act Density 0.029%

    No Known Activations