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

    Neuronpedia

    INDEX
    Explanations

    quotes starting with the word "says"

    oai_token-act-pair · gpt-3.5-turbo

    instances of speech or quotations attributed to individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rats
    -0.72
    inary
    -0.70
    nerg
    -0.68
    cffffcc
    -0.64
     caliber
    -0.64
    swick
    -0.61
    wives
    -0.61
     blows
    -0.60
     overfl
    -0.59
     cess
    -0.59
    POSITIVE LOGITS
    omething
    0.97
    ynthesis
    0.93
    ometimes
    0.84
    hiba
    0.83
    omorph
    0.78
    paces
    0.78
    olate
    0.78
    ynt
    0.76
    creen
    0.76
     Zup
    0.75
    Act Density 0.101%

    No Known Activations