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

    Neuronpedia

    INDEX
    Explanations

    mixed activations with a focus on various words and phrases, including names of people and locations

    oai_token-act-pair · gpt-3.5-turbo

    letter combinations and specific sequences resembling proper nouns or names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     looph
    -0.75
     exting
    -0.70
    EStreamFrame
    -0.65
     subur
    -0.64
    ¥ŀ
    -0.63
     eleph
    -0.63
     millenn
    -0.63
    aditional
    -0.60
     tacit
    -0.60
    ailable
    -0.59
    POSITIVE LOGITS
    ®
    0.68
    phia
    0.68
    cious
    0.66
    ãĤ£
    0.66
    abilia
    0.64
    ronics
    0.64
    eni
    0.63
    ippi
    0.62
    illus
    0.61
    _-
    0.60
    Act Density 0.698%

    No Known Activations