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

    Neuronpedia

    INDEX
    Explanations

    words or phrases containing a specific sequence of characters "Z"

    oai_token-act-pair · gpt-3.5-turbo

    strings of characters or links, potentially representing user handles or identifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    itures
    -0.78
    cers
    -0.71
    naissance
    -0.69
    croft
    -0.69
    Interstitial
    -0.67
    riott
    -0.66
    ãĥ¼ãĥĨ
    -0.65
    20439
    -0.64
    nces
    -0.63
    ateurs
    -0.63
    POSITIVE LOGITS
    ombie
    1.39
    ombies
    1.34
    ebra
    1.14
    ERO
    1.09
    odiac
    1.04
    eros
    1.03
    oom
    1.00
    ymes
    0.97
    ealous
    0.96
    ONE
    0.96
    Act Density 0.014%

    No Known Activations