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

    Neuronpedia

    INDEX
    Explanations

    capital letters Z followed by different numbers

    oai_token-act-pair · gpt-3.5-turbo

    specific alphanumeric sequences, likely URLs or identifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    itures
    -0.82
    croft
    -0.72
     Cheong
    -0.70
    20439
    -0.68
    ãĥ¼ãĥĨ
    -0.67
    riott
    -0.65
    Interstitial
    -0.65
    ateurs
    -0.65
    naissance
    -0.64
     thous
    -0.64
    POSITIVE LOGITS
    ombie
    1.32
    ombies
    1.27
    ebra
    1.13
    ERO
    1.05
    odiac
    1.03
    ealous
    1.01
    eros
    1.00
    hao
    0.99
    ymes
    0.95
    oom
    0.91
    Act Density 0.020%

    No Known Activations