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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to a specific individual or event

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "br" or variations indicating breaks or separations in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eers
    -0.82
    WARE
    -0.71
    STER
    -0.69
    WARN
    -0.69
     Totem
    -0.68
     DEBUG
    -0.66
    meal
    -0.65
    Sax
    -0.63
     AMERICA
    -0.63
    ographed
    -0.62
    POSITIVE LOGITS
    ackets
    1.12
    igham
    1.08
    acket
    1.06
    anches
    0.96
    ained
    0.94
    ighter
    0.92
    aced
    0.91
    ains
    0.90
    anch
    0.90
    andon
    0.89
    Act Density 0.010%

    No Known Activations