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

    Neuronpedia

    INDEX
    Explanations

    words related to technical instructions and specifications

    oai_token-act-pair · gpt-3.5-turbo

    phrases that describe purpose or function

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    beat
    -0.71
    chenko
    -0.69
    å£
    -0.68
    alan
    -0.68
    illin
    -0.66
    edin
    -0.65
    ivil
    -0.65
    Russ
    -0.64
    âĶĢ
    -0.63
    owsky
    -0.61
    POSITIVE LOGITS
    gery
    1.17
    bidden
    1.10
     purposes
    1.07
     example
    1.03
     instance
    1.01
    geries
    0.98
     determining
    0.96
     debugging
    0.93
     starters
    0.91
    aging
    0.90
    Act Density 0.252%

    No Known Activations