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

    Neuronpedia

    INDEX
    Explanations

    numbers with decimals

    oai_token-act-pair · gpt-3.5-turbo

    numeric values followed by a period

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anus
    -0.74
     cradle
    -0.72
     administrator
    -0.68
     consistency
    -0.68
     mimic
    -0.67
    itionally
    -0.67
     portrait
    -0.66
     proactive
    -0.66
     champion
    -0.65
     arms
    -0.64
    POSITIVE LOGITS
    Downloadha
    1.33
    00
    1.15
    sbm
    1.09
    99
    1.07
    75
    0.98
    5
    0.98
    50
    0.98
    95
    0.97
    jpg
    0.97
    80
    0.97
    Act Density 0.162%

    No Known Activations