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

    Neuronpedia

    INDEX
    Explanations

    words related to a specific type of programming code or formatting

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "escape."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥĦ
    -0.72
     è£ıè
    -0.68
    gran
    -0.68
    ĪĴ
    -0.68
    winner
    -0.67
    ãĥĥãĥĪ
    -0.66
    boys
    -0.66
    beard
    -0.66
    Fram
    -0.63
    tery
    -0.62
    POSITIVE LOGITS
    aped
    1.23
    ribed
    1.20
    ript
    1.06
    apes
    1.04
    ence
    1.03
    utions
    1.01
    apers
    0.96
    ission
    0.95
    itation
    0.95
    opes
    0.94
    Act Density 0.014%

    No Known Activations