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

    Neuronpedia

    INDEX
    Explanations

    names of people or places

    oai_token-act-pair · gpt-3.5-turbo

    references to groups or collectives, particularly in relation to animals or populations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     peel
    -0.77
    cyclopedia
    -0.75
     decomp
    -0.74
    FK
    -0.74
    ructose
    -0.74
     capacitor
    -0.72
    lear
    -0.67
    ibble
    -0.67
    Agent
    -0.65
     enthus
    -0.65
    POSITIVE LOGITS
    į
    0.83
     Rasm
    0.83
    hammad
    0.80
     Mehran
    0.73
    angelo
    0.73
     Kirin
    0.73
     herds
    0.72
     Lah
    0.70
     Lars
    0.70
     Karin
    0.69
    Act Density 0.029%

    No Known Activations