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

    Neuronpedia

    INDEX
    Explanations

    words related to controversial medical issues and their implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Wunused
    -0.15
    ÅĻel
    -0.15
    ripple
    -0.15
    ãi
    -0.14
    Schedulers
    -0.14
    @brief
    -0.14
    å±ĭ
    -0.14
    ÙĪÙ¾
    -0.14
    pei
    -0.14
    ahi
    -0.14
    POSITIVE LOGITS
     staging
    0.16
     alone
    0.15
    orio
    0.14
    noop
    0.14
     lone
    0.14
    poses
    0.14
    idal
    0.14
    imer
    0.13
    .gov
    0.13
     fals
    0.13
    Act Density 0.004%

    No Known Activations