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

    Neuronpedia

    INDEX
    Explanations

    occurances of the word "ext" followed by a number

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "ext" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SHIP
    -0.82
    ãĤ´ãĥ³
    -0.82
    geist
    -0.79
    folk
    -0.78
    igans
    -0.70
    hari
    -0.68
     apprentice
    -0.65
    ãĤ°
    -0.65
    cht
    -0.65
    iard
    -0.65
    POSITIVE LOGITS
    raction
    1.21
    ension
    1.19
    ention
    1.15
    ensions
    1.15
    ract
    1.11
    itud
    1.10
    ensive
    1.09
    racted
    1.09
    ortion
    1.08
    ENDED
    1.07
    Act Density 0.018%

    No Known Activations