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

    Neuronpedia

    INDEX
    Explanations

    phrases related to questioning and speculation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    -equiv
    -0.14
    家çļĦ
    -0.14
    amage
    -0.14
    cimal
    -0.14
    aes
    -0.13
    ungan
    -0.13
    odont
    -0.13
    zar
    -0.13
    -ves
    -0.13
     hence
    -0.13
    POSITIVE LOGITS
    ushman
    0.18
    acus
    0.17
    yo
    0.16
    olet
    0.16
    SYM
    0.16
    ocket
    0.15
    pector
    0.14
     Holl
    0.14
    oa
    0.14
    ez
    0.14
    Act Density 0.037%

    No Known Activations