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

    Neuronpedia

    INDEX
    Explanations

    phrases and words related to proven methods or experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pp
    -0.15
     htmlentities
    -0.15
    iful
    -0.14
    erte
    -0.14
    pp
    -0.14
    itch
    -0.14
    eland
    -0.14
    WXYZ
    -0.14
    anik
    -0.14
    erp
    -0.13
    POSITIVE LOGITS
     trib
    0.29
     tested
    0.29
     proven
    0.27
     Tested
    0.25
    -tested
    0.25
     Trib
    0.23
     testing
    0.23
    tested
    0.21
     error
    0.20
     test
    0.20
    Act Density 0.013%

    No Known Activations