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

    Neuronpedia

    INDEX
    Explanations

    words related to hazards and safety concerns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    igin
    -0.16
    iaux
    -0.15
    andi
    -0.15
    ersh
    -0.14
    onda
    -0.14
    jon
    -0.14
    imax
    -0.14
    sta
    -0.14
    olia
    -0.13
    oria
    -0.13
    POSITIVE LOGITS
    rus
    0.17
    abal
    0.16
    tgt
    0.15
    uble
    0.15
     Abbas
    0.14
    gün
    0.14
     Ashe
    0.14
     dazu
    0.14
    unsafe
    0.14
    esson
    0.14
    Act Density 0.009%

    No Known Activations