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

    Neuronpedia

    INDEX
    Explanations

    phrases related to figurative language, especially the use of the word "proverbial"

    oai_token-act-pair · gpt-3.5-turbo

    character encoding errors or non-standard characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alez
    -0.74
    icter
    -0.71
    odon
    -0.70
    asser
    -0.69
    ified
    -0.69
    orne
    -0.68
    inctions
    -0.68
    ulhu
    -0.68
    alion
    -0.68
    iple
    -0.67
    POSITIVE LOGITS
    ¢
    1.04
    ÃĤ
    0.98
    ©
    0.95
    HL
    0.82
    ³³³³
    0.82
    ¶
    0.79
    §
    0.79
    ³³³³³³³³³³³³³³³³
    0.78
    ¯¯
    0.78
    £
    0.76
    Act Density 0.007%

    No Known Activations