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

    Neuronpedia

    INDEX
    Explanations

    terms related to potential harm or danger in a medical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    asley
    -0.17
     ones
    -0.16
    lä
    -0.16
     же
    -0.15
    lier
    -0.15
    ilis
    -0.15
    zin
    -0.15
    stra
    -0.14
     Ones
    -0.14
     вол
    -0.14
    POSITIVE LOGITS
    ode
    0.14
    rors
    0.14
    osi
    0.14
    toa
    0.14
    çķª
    0.14
    iyel
    0.14
    oshi
    0.13
    ãĥ©ãĤ¯
    0.13
     chac
    0.13
    osal
    0.13
    Act Density 0.202%

    No Known Activations