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

    Neuronpedia

    INDEX
    Explanations

    locations or landmarks

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, specifically names and places

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    GROUP
    -0.75
     scratch
    -0.71
    âĶĢâĶĢâĶĢâĶĢ
    -0.69
     NETWORK
    -0.68
     millennials
    -0.66
     wardrobe
    -0.65
     Millenn
    -0.65
     academ
    -0.65
     millennial
    -0.65
     sibling
    -0.63
    POSITIVE LOGITS
    anus
    1.19
    bah
    1.11
    anski
    1.09
    arius
    1.09
    oba
    1.09
    alli
    1.08
    bol
    1.07
    tera
    1.07
    onga
    1.06
    ovo
    1.06
    Act Density 0.491%

    No Known Activations