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

    Neuronpedia

    INDEX
    Explanations

    descriptions and mentions of diagrams

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "diagram" and related visual presentation terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    NetMessage
    -0.72
    ierra
    -0.70
    Interstitial
    -0.70
    Chance
    -0.69
    earned
    -0.68
     rainy
    -0.67
     diligence
    -0.63
    akening
    -0.63
     indefinite
    -0.63
    VO
    -0.62
    POSITIVE LOGITS
     diagram
    1.23
     diagrams
    1.20
    matically
    0.92
    matical
    0.90
    zag
    0.89
    matic
    0.83
    ming
    0.82
     schematic
    0.79
    rast
    0.79
    odynam
    0.77
    Act Density 0.004%

    No Known Activations