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

    Neuronpedia

    INDEX
    Explanations

    instances of compliance and procedural language

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    olut
    -0.16
    uchs
    -0.15
    ams
    -0.15
    ocale
    -0.15
    thon
    -0.14
    oble
    -0.14
    εÏį
    -0.14
    uitka
    -0.14
    apixel
    -0.14
    zin
    -0.13
    POSITIVE LOGITS
     Amazon
    0.14
    mazon
    0.14
    PREFIX
    0.14
    باش
    0.14
     âķ
    0.13
     passage
    0.13
    ister
    0.13
    gan
    0.13
    _INCLUDED
    0.13
     abund
    0.13
    Act Density 0.182%

    No Known Activations