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

    Neuronpedia

    INDEX
    Explanations

    definite articles and phrases related to distinct entities or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    abyrinth
    -0.17
    eg
    -0.16
    igu
    -0.15
    egade
    -0.15
    STITUTE
    -0.14
     various
    -0.14
    suz
    -0.13
    ohan
    -0.13
    onen
    -0.13
    ád
    -0.13
    POSITIVE LOGITS
     only
    0.28
     ONLY
    0.25
    only
    0.22
     Only
    0.22
    oret
    0.21
     third
    0.20
     second
    0.20
    ONLY
    0.19
     result
    0.19
    _ONLY
    0.18
    Act Density 0.173%

    No Known Activations