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

    Neuronpedia

    INDEX
    Explanations

    titles of books

    oai_token-act-pair · gpt-3.5-turbo

    titles of books or publications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    undai
    -0.82
     trouble
    -0.73
    bered
    -0.72
    rost
    -0.71
    roth
    -0.68
    yan
    -0.68
    gomery
    -0.67
    outube
    -0.66
    xon
    -0.65
     overl
    -0.64
    POSITIVE LOGITS
     Definitive
    1.19
     Causes
    1.06
     Lessons
    1.05
     Principles
    1.00
     Moving
    0.97
     Volume
    0.97
     Tactics
    0.96
     Reloaded
    0.96
     Memories
    0.91
     Rise
    0.91
    Act Density 0.070%

    No Known Activations