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

    Neuronpedia

    INDEX
    Explanations

    references to source code in technical documentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    interstitial
    -0.85
    aeper
    -0.82
    poons
    -0.81
    hap
    -0.78
    ornings
    -0.74
    undown
    -0.71
    uckle
    -0.71
    okers
    -0.71
    ategory
    -0.71
    outh
    -0.70
    POSITIVE LOGITS
    forge
    1.08
    books
    0.94
     code
    0.94
    Fed
    0.91
    kit
    0.90
    book
    0.89
    Forge
    0.85
     Gutenberg
    0.83
     material
    0.78
     whence
    0.78
    Act Density 0.015%

    No Known Activations