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

    Neuronpedia

    INDEX
    Explanations

    references to conventional practices or methods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ierre
    -0.15
     Lawson
    -0.14
     material
    -0.14
    947
    -0.14
    addir
    -0.14
    940
    -0.14
    ãģ®ãģĮ
    -0.13
     bid
    -0.13
    erre
    -0.13
     Mist
    -0.13
    POSITIVE LOGITS
    ziel
    0.16
    visor
    0.16
    luet
    0.15
    ymous
    0.15
    viso
    0.15
    -common
    0.15
    shal
    0.14
    mpar
    0.14
    ately
    0.14
    ized
    0.14
    Act Density 0.019%

    No Known Activations