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

    Neuronpedia

    INDEX
    Explanations

    phrases related to proper nouns, possibly names and locations

    oai_token-act-pair · gpt-3.5-turbo

    different forms and variations of the word "brot" and related terms, potentially highlighting food or bakery items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    代
    -0.73
    ãĤ¨ãĥ«
    -0.71
    ŃĶ
    -0.70
    NPR
    -0.69
    ãĥ´
    -0.68
    ãĥ¤
    -0.66
    VIDEO
    -0.65
     grap
    -0.65
     subscribing
    -0.64
    ¿½
    -0.62
    POSITIVE LOGITS
    hire
    0.83
    enged
    0.83
     Cavern
    0.81
    chers
    0.80
    glers
    0.79
    ters
    0.78
    cher
    0.78
    heit
    0.77
     Manor
    0.75
    levard
    0.75
    Act Density 0.339%

    No Known Activations