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

    Neuronpedia

    INDEX
    Explanations

    proper names in a text

    oai_token-act-pair · gpt-3.5-turbo

    names of people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    GoldMagikarp
    -0.88
    ModLoader
    -0.81
    20439
    -0.74
    Congratulations
    -0.70
    RIP
    -0.69
    Loading
    -0.67
    Roaming
    -0.67
    dL
    -0.67
    Dad
    -0.67
    OURCE
    -0.66
    POSITIVE LOGITS
    sson
    1.29
    kson
    1.05
    ovich
    0.98
    owicz
    0.94
     Morse
    0.87
    enson
    0.86
    ovsky
    0.86
    cock
    0.81
    eson
    0.81
     Mercer
    0.79
    Act Density 0.193%

    No Known Activations