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

    Neuronpedia

    INDEX
    Explanations

    words related to structured forms or formats

    oai_token-act-pair · gpt-3.5-turbo

    references to different forms of the word "form."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Decker
    -0.66
     Maya
    -0.65
     Berkshire
    -0.64
    faced
    -0.64
     Solitaire
    -0.63
    prints
    -0.63
     Marcos
    -0.61
    BUT
    -0.60
    built
    -0.59
     FTA
    -0.59
    POSITIVE LOGITS
    orm
    1.33
    orph
    1.11
    ont
    1.11
    omon
    1.03
    ophon
    1.03
    orthy
    1.01
    etheus
    0.99
    agnetic
    0.96
    itte
    0.94
    inational
    0.93
    Act Density 0.005%

    No Known Activations