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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating problems or concerns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    egis
    -0.15
    atura
    -0.14
    ury
    -0.14
    Ïģκε
    -0.14
    اÙĨÙĩ
    -0.13
    Reserved
    -0.13
    _SAFE
    -0.13
     DÃŃky
    -0.13
    .initState
    -0.13
    _normalize
    -0.13
    POSITIVE LOGITS
    éļ
    0.17
     cost
    0.15
    672
    0.15
     conquer
    0.15
     conquered
    0.15
    jed
    0.15
    isman
    0.15
     expense
    0.14
     prospect
    0.14
    adin
    0.14
    Act Density 0.101%

    No Known Activations