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

    Neuronpedia

    INDEX
    Explanations

    proper nouns or phrases related to specific geographic locations

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "vi" or variations of it, likely indicating a focus on visual content or visual media

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    */(
    -0.94
     Cosponsors
    -0.79
    corn
    -0.71
    landish
    -0.70
    bread
    -0.69
    lins
    -0.68
    raising
    -0.64
    stro
    -0.63
    rules
    -0.63
    lain
    -0.62
    POSITIVE LOGITS
    Äį
    0.88
    ulner
    0.87
    agra
    0.86
    ñ
    0.86
    Äĩ
    0.84
    udence
    0.83
    ISION
    0.83
     versa
    0.82
    irus
    0.81
    apore
    0.80
    Act Density 0.015%

    No Known Activations