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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate controversy or disagreement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    elho
    -0.17
    teÅŁ
    -0.15
     yourselves
    -0.14
    ibel
    -0.13
    ITCH
    -0.13
    agnost
    -0.13
    áme
    -0.13
     ...\
    -0.13
    alloc
    -0.13
    uels
    -0.13
    POSITIVE LOGITS
    ifa
    0.19
     unsur
    0.15
     Gund
    0.14
    sharp
    0.14
     PMID
    0.14
    ž
    0.14
    ÑĢав
    0.14
     Monad
    0.14
    625
    0.14
    BarButton
    0.14
    Act Density 0.100%

    No Known Activations