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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, especially names of people

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names of people and notable identifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ength
    -0.85
    é¾į
    -0.81
    psons
    -0.80
    oled
    -0.79
    ously
    -0.79
    oured
    -0.78
    ize
    -0.78
    opol
    -0.77
    saf
    -0.76
    osal
    -0.75
    POSITIVE LOGITS
     Bie
    1.34
     Tuc
    0.88
     Dele
    0.77
    kson
    0.77
     Wyatt
    0.76
    braska
    0.75
    CU
    0.75
     Gunn
    0.74
     Akin
    0.74
     Reeves
    0.73
    Act Density 0.018%

    No Known Activations