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

    Neuronpedia

    INDEX
    Explanations

    phrases related to a broad range of topics, such as politics, personal responsibility, and specific cultural groups

    oai_token-act-pair · gpt-3.5-turbo

    references to collective entities or groups and their experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ¶
    -0.68
    MSN
    -0.57
    KT
    -0.56
     Kinnikuman
    -0.56
     Profile
    -0.55
    rez
    -0.55
    ocene
    -0.55
    ++++++++++++++++
    -0.54
    trak
    -0.53
    âľ
    -0.53
    POSITIVE LOGITS
     consequ
    1.21
     subsequent
    1.06
     consequently
    0.98
     ensuing
    0.93
     thereto
    0.91
     alike
    0.87
     thereafter
    0.86
     thereof
    0.82
     accompanying
    0.81
     thereby
    0.80
    Act Density 0.671%

    No Known Activations