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

    Neuronpedia

    INDEX
    Explanations

    things that are physically connected or attached to something else

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate attachment or connection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    audi
    -0.79
    geist
    -0.74
    lich
    -0.72
    RD
    -0.70
    iren
    -0.70
    vier
    -0.68
    iosity
    -0.68
    llor
    -0.67
    cens
    -0.64
    chlor
    -0.64
    POSITIVE LOGITS
     Siber
    0.75
     orbit
    0.73
     handle
    0.73
     GPIO
    0.72
     Equip
    0.71
     shore
    0.68
     Interstate
    0.68
     assist
    0.67
     underside
    0.66
     schedule
    0.66
    Act Density 0.174%

    No Known Activations