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

    Neuronpedia

    INDEX
    Explanations

    URLs or file paths

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the verb "be."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Rab
    -0.69
    rones
    -0.69
     Notting
    -0.67
     Blitz
    -0.65
    lights
    -0.62
    erity
    -0.62
     cease
    -0.60
     Mans
    -0.60
     1922
    -0.60
     Desire
    -0.59
    POSITIVE LOGITS
     traced
    1.10
     viewed
    1.08
     seen
    1.01
     easily
    1.01
     likened
    1.00
     construed
    0.93
     forgiven
    0.92
     accessed
    0.90
     considered
    0.88
     summarized
    0.86
    Act Density 0.099%

    No Known Activations