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

    Neuronpedia

    INDEX
    Explanations

    references to conflict and confrontation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iero
    -0.17
    UBY
    -0.17
    è·µ
    -0.15
    Reusable
    -0.15
    еÑĢин
    -0.15
    elm
    -0.15
    elen
    -0.14
    ÑijÑĢ
    -0.14
    uby
    -0.14
    ActionButton
    -0.14
    POSITIVE LOGITS
     unable
    0.20
    ä¸įå¾Ĺ
    0.20
     vulnerabilities
    0.19
     cant
    0.19
     incapable
    0.18
     cannot
    0.18
     retreat
    0.18
     fal
    0.18
     forced
    0.18
     Cant
    0.18
    Act Density 0.320%

    No Known Activations