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

    Neuronpedia

    INDEX
    Explanations

    words related to technical terms and concepts

    oai_token-act-pair · gpt-3.5-turbo

    words and suffixes related to technology and specific technical terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     stub
    -0.60
     suc
    -0.59
     ordinary
    -0.58
     NPR
    -0.58
     epist
    -0.57
    ij士
    -0.56
     Ike
    -0.56
    ĸļ
    -0.56
     unmarked
    -0.56
     authoritative
    -0.55
    POSITIVE LOGITS
    ALLY
    0.89
    ulic
    0.88
    geist
    0.80
    IUM
    0.78
    agate
    0.76
    hod
    0.75
    llo
    0.75
    ulhu
    0.74
    ronics
    0.71
    Sov
    0.71
    Act Density 0.503%

    No Known Activations