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

    Neuronpedia

    INDEX
    Explanations

    references to software components and programming elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vl
    -0.16
    LU
    -0.15
     steep
    -0.15
    wel
    -0.15
    esign
    -0.14
    Ñī
    -0.14
    Å¡ov
    -0.14
    ylum
    -0.14
     scrambled
    -0.13
    ycl
    -0.13
    POSITIVE LOGITS
     determin
    0.16
     determ
    0.15
    itel
    0.15
    inox
    0.14
    ading
    0.14
    arias
    0.14
    arios
    0.14
    allon
    0.14
    ĽĪ
    0.13
    ãģ«ãģĹãģ¦
    0.13
    Act Density 0.002%

    No Known Activations