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

    Neuronpedia

    INDEX
    Explanations

    Terms and phrases that indicate significant values or notable characteristics across various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    è«ĩ
    -0.16
    ÑĤÑİ
    -0.15
    iferay
    -0.15
    èĨľ
    -0.15
    itemid
    -0.15
    çĶļ
    -0.15
    STDOUT
    -0.14
     pent
    -0.14
    idy
    -0.14
    jo
    -0.14
    POSITIVE LOGITS
    etto
    0.22
    ALI
    0.17
    биÑĤ
    0.17
    fm
    0.16
    iego
    0.16
    udes
    0.15
    .Abstractions
    0.15
    ato
    0.15
     Greens
    0.14
     Credentials
    0.14
    Act Density 0.020%

    No Known Activations