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

    Neuronpedia

    INDEX
    Explanations

    topics related to official documentation and government processes

    oai_token-act-pair · gpt-3.5-turbo

    terms related to sports, events, and significant milestones

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    problem
    -0.70
     outbreak
    -0.69
     shower
    -0.68
     bunch
    -0.67
     process
    -0.67
    cients
    -0.65
    ressor
    -0.65
    artment
    -0.65
    ramid
    -0.64
    ividual
    -0.63
    POSITIVE LOGITS
    speak
    1.04
     parity
    0.99
     proportions
    0.97
     fame
    0.88
     immortality
    0.87
     territory
    0.81
    Semitism
    0.80
     supremacy
    0.77
     Dragonbound
    0.72
     heaven
    0.72
    Act Density 1.180%

    No Known Activations