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

    Neuronpedia

    INDEX
    Explanations

    references to threats or dangers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    adol
    -0.16
    acements
    -0.15
    à¸Ńà¸Ķ
    -0.15
     Marty
    -0.15
     Trojan
    -0.14
    ispens
    -0.14
    ingleton
    -0.14
    eki
    -0.14
     Dale
    -0.14
     _$
    -0.14
    POSITIVE LOGITS
     Lady
    0.21
    Lady
    0.20
     Lord
    0.16
    lady
    0.16
     K
    0.15
     sor
    0.15
     vrou
    0.15
     advent
    0.14
     chrono
    0.14
    .guild
    0.14
    Act Density 0.604%

    No Known Activations