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

    Neuronpedia

    INDEX
    Explanations

    phrases related to ability and potential actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    warts
    -0.16
    isty
    -0.16
    allon
    -0.16
    unik
    -0.15
    ilion
    -0.15
    allah
    -0.15
    storybook
    -0.14
    upp
    -0.14
    reed
    -0.14
    erland
    -0.14
    POSITIVE LOGITS
    aes
    0.15
    comm
    0.14
    ssi
    0.14
    Dealer
    0.14
    addtogroup
    0.14
    roz
    0.14
    chan
    0.13
    æĭ¥
    0.13
    est
    0.13
    yum
    0.13
    Act Density 0.129%

    No Known Activations