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

    Neuronpedia

    INDEX
    Explanations

    mentions of proper nouns or names

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of the name "Mar."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ħĭ
    -0.98
    éĹĺ
    -0.87
    culosis
    -0.85
    é¾įå¥ij士
    -0.76
    ngth
    -0.72
    anwhile
    -0.71
    CRIP
    -0.71
    mble
    -0.67
     Chosen
    -0.65
    =]
    -0.64
    POSITIVE LOGITS
    Mar
    0.98
    riage
    0.96
    ital
    0.96
    ried
    0.95
    riages
    0.93
    lene
    0.85
    ousing
    0.85
    isco
    0.83
    azz
    0.83
     Mar
    0.83
    Act Density 0.012%

    No Known Activations