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

    Neuronpedia

    INDEX
    Explanations

    numbers corresponding to specific times of the day

    oai_token-act-pair · gpt-3.5-turbo

    references to numerical values and measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    76561
    -0.72
    Agent
    -0.72
     Emblem
    -0.72
    ntil
    -0.70
     Cutter
    -0.69
    Ô
    -0.68
    SourceFile
    -0.66
     Nun
    -0.65
     Totem
    -0.65
     Arpaio
    -0.64
    POSITIVE LOGITS
    ino
    0.77
     strokes
    0.71
    Pg
    0.70
     percent
    0.70
     respectively
    0.70
    eele
    0.70
    cm
    0.69
    negie
    0.68
     minutes
    0.67
     districts
    0.66
    Act Density 0.128%

    No Known Activations