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

    Neuronpedia

    INDEX
    Explanations

    percentage changes

    oai_token-act-pair · gpt-3.5-turbo

    percentages and statistical data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rients
    -0.78
    objects
    -0.73
     Learns
    -0.72
    ateurs
    -0.71
    rities
    -0.71
    eworks
    -0.70
    links
    -0.70
     guiName
    -0.70
    events
    -0.70
    SPONSORED
    -0.70
    POSITIVE LOGITS
     advisory
    0.80
     burner
    0.78
     expansion
    0.78
     timer
    0.77
     tornado
    0.77
     revolving
    0.77
     lawsuit
    0.76
     operation
    0.76
     endorsement
    0.76
     affidavit
    0.75
    Act Density 0.167%

    No Known Activations