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

    Neuronpedia

    INDEX
    Explanations

    specialized terms or names, like "Marissa" or "Joel Gilbert."

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of the name "Mar" associated with different contexts or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    éĹĺ
    -0.95
    ħĭ
    -0.91
    é¾įå¥ij士
    -0.78
     tray
    -0.78
    anwhile
    -0.75
    ngth
    -0.75
    cipline
    -0.73
    ij士
    -0.70
     Regulatory
    -0.69
    uyomi
    -0.68
    POSITIVE LOGITS
    riages
    1.14
    riage
    1.03
    ital
    1.01
    lene
    1.00
    ried
    1.00
    ice
    0.96
    azz
    0.95
    iscal
    0.92
    oon
    0.90
    aqu
    0.90
    Act Density 0.015%

    No Known Activations