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

    Neuronpedia

    INDEX
    Explanations

    expressions of boredom or repetitiveness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erdale
    -0.17
    zzle
    -0.16
    Ãłi
    -0.15
    ameleon
    -0.14
    IMITIVE
    -0.14
    째
    -0.14
    912
    -0.14
    ix
    -0.13
    eut
    -0.13
     ado
    -0.13
    POSITIVE LOGITS
     boring
    0.18
     bored
    0.16
    émon
    0.15
    _rsp
    0.15
    sville
    0.15
    Rob
    0.14
     Rolling
    0.14
    ÙħÙĦØ©
    0.14
    енно
    0.13
    acker
    0.13
    Act Density 0.030%

    No Known Activations