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

    Neuronpedia

    INDEX
    Explanations

    references to driving and safety concerns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    coles
    -0.17
     crem
    -0.15
    rance
    -0.15
     pip
    -0.15
    cole
    -0.15
    aj
    -0.15
    istrovstvÃŃ
    -0.14
    ansi
    -0.14
     bun
    -0.14
    omp
    -0.13
    POSITIVE LOGITS
     designate
    0.19
     sober
    0.18
     designated
    0.18
    éĨ
    0.17
     designation
    0.16
     Driving
    0.15
    945
    0.15
     доз
    0.15
    uez
    0.15
    _design
    0.14
    Act Density 0.027%

    No Known Activations