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

    Neuronpedia

    INDEX
    Explanations

    the term "ext" along with a number following it

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the prefix "ext" indicating extensions or variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    shall
    -0.68
     Shen
    -0.67
     Goods
    -0.66
     Soldiers
    -0.65
    town
    -0.65
    Town
    -0.65
    lah
    -0.64
    gear
    -0.64
     Sands
    -0.64
    oking
    -0.64
    POSITIVE LOGITS
     ext
    4.04
     Ext
    1.90
    ext
    1.43
    Ext
    1.27
     EXT
    1.13
     abduct
    0.98
     Extension
    0.92
     extr
    0.90
     Intro
    0.89
     abs
    0.88
    Act Density 0.007%

    No Known Activations