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

    Neuronpedia

    INDEX
    Explanations

    words related to frustration or confusion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ueue
    -0.20
    ffe
    -0.19
    UED
    -0.19
    EMPLARY
    -0.19
    ODEV
    -0.17
    uela
    -0.17
    Äįka
    -0.17
    _Tis
    -0.16
    TRGL
    -0.16
    meni
    -0.16
    POSITIVE LOGITS
    um
    0.39
    ub
    0.33
    up
    0.32
    ul
    0.32
    ur
    0.31
    uk
    0.31
    ut
    0.31
    ud
    0.28
    un
    0.27
    av
    0.27
    Act Density 0.026%

    No Known Activations