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

    Neuronpedia

    INDEX
    Explanations

    discussions around safety, responsibility, and requirements related to handling firearms and medications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rang
    -0.17
    ivan
    -0.15
    alm
    -0.15
    boom
    -0.15
    ваÑĤи
    -0.14
    arty
    -0.14
    lok
    -0.14
    ress
    -0.14
    lichkeit
    -0.14
    ÑĢеб
    -0.13
    POSITIVE LOGITS
     safety
    0.19
    afety
    0.16
    abbo
    0.16
    pcm
    0.15
    askan
    0.15
    ode
    0.15
     danger
    0.15
    CLS
    0.15
     Safety
    0.15
     Ris
    0.14
    Act Density 0.220%

    No Known Activations