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

    Neuronpedia

    INDEX
    Explanations

    dates and numbers represented in a specific format

    oai_token-act-pair · gpt-3.5-turbo

    numeric values and related data points

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    EStream
    -0.65
     clos
    -0.65
     ISIL
    -0.64
     pitched
    -0.59
     secrecy
    -0.59
     libel
    -0.58
     ç¥ŀ
    -0.58
     insulting
    -0.58
     engineering
    -0.57
     pencil
    -0.57
    POSITIVE LOGITS
    4
    3.14
    3
    2.43
    5
    2.39
    6
    2.27
    2
    2.23
    8
    2.16
    7
    2.07
    9
    1.93
    1
    1.92
    0
    1.69
    Act Density 0.033%

    No Known Activations