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

    Neuronpedia

    INDEX
    Explanations

    references to syntax and usage in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ungs
    -0.17
    ning
    -0.16
    ãĥ³ãĤ°
    -0.16
    atis
    -0.15
    arial
    -0.15
    rey
    -0.15
     Lust
    -0.14
    col
    -0.14
    benh
    -0.14
    832
    -0.13
    POSITIVE LOGITS
    orea
    0.15
    elong
    0.15
    agara
    0.15
    ramids
    0.15
    ffset
    0.15
    dden
    0.15
    ãĤ¦ãĥ³
    0.14
    ramid
    0.14
    eriod
    0.14
    istory
    0.14
    Act Density 0.031%

    No Known Activations