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

    Neuronpedia

    INDEX
    Explanations

    strings and their attributes within code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    goo
    -0.17
    etro
    -0.16
    hazi
    -0.15
    byname
    -0.15
    Ñģли
    -0.15
    synthesize
    -0.15
     sud
    -0.14
    .googleapis
    -0.14
    go
    -0.14
    ATS
    -0.14
    POSITIVE LOGITS
    ruba
    0.15
    aptive
    0.14
    опол
    0.14
    InOut
    0.13
    -ÑĤ
    0.13
     Doch
    0.13
    opro
    0.13
    ellas
    0.13
    ÅĤad
    0.13
     |--
    0.13
    Act Density 0.024%

    No Known Activations