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

    Neuronpedia

    INDEX
    Explanations

    words related to people's names

    oai_token-act-pair · gpt-3.5-turbo

    sequences of letters that resemble the structure of personal names and other proper nouns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    »Ĵ
    -0.66
     Palest
    -0.66
    ãĤ¤ãĥĪ
    -0.66
     Pigs
    -0.65
     CLICK
    -0.59
    CHA
    -0.58
     Lovely
    -0.58
    HAHAHAHA
    -0.58
    vertisement
    -0.58
    é¾
    -0.57
    POSITIVE LOGITS
    aults
    0.74
    ember
    0.71
    onymous
    0.70
    eper
    0.70
    abo
    0.68
    ecast
    0.68
    wed
    0.67
    fried
    0.66
    avy
    0.66
    igham
    0.66
    Act Density 0.081%

    No Known Activations