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

    Neuronpedia

    INDEX
    Explanations

    terms related to manipulation and deception

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ekl
    -0.17
    eum
    -0.15
    зÑĮ
    -0.15
    unce
    -0.15
    umi
    -0.15
    yen
    -0.14
    ingers
    -0.14
    ignet
    -0.14
    GenerationStrategy
    -0.14
    ROC
    -0.13
    POSITIVE LOGITS
    ëĭ¤ê°Ģ
    0.18
    lez
    0.15
     Viv
    0.15
    ctic
    0.15
    sez
    0.14
    asted
    0.14
    NST
    0.14
    istor
    0.14
    gorm
    0.14
     Towards
    0.13
    Act Density 0.172%

    No Known Activations