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

    Neuronpedia

    INDEX
    Explanations

    aliases or pseudonyms

    oai_token-act-pair · gpt-3.5-turbo

    references to aliases or pseudonyms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    asted
    -0.82
    cept
    -0.80
    icles
    -0.78
    icle
    -0.77
    odcast
    -0.77
    yg
    -0.74
    secut
    -0.74
    urrent
    -0.73
    ighth
    -0.73
    audio
    -0.72
    POSITIVE LOGITS
     alias
    0.99
     aliases
    0.78
    =""
    0.77
    ename
    0.76
    =]
    0.75
     ali
    0.73
     versa
    0.72
    isSpecialOrderable
    0.72
     Carbuncle
    0.72
    BILITIES
    0.71
    Act Density 0.017%

    No Known Activations