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

    Neuronpedia

    INDEX
    Explanations

    key terms related to legal and liability issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    reon
    -0.18
    /locale
    -0.17
    éru
    -0.17
    ÃŃo
    -0.16
    loh
    -0.16
    ertz
    -0.16
    rrha
    -0.15
    odesk
    -0.15
    npos
    -0.15
    eriod
    -0.15
    POSITIVE LOGITS
    i
    0.17
     undis
    0.16
    oren
    0.15
    oke
    0.15
    ÑĢак
    0.14
    working
    0.14
    RSA
    0.14
     Candy
    0.14
    et
    0.14
     micro
    0.14
    Act Density 0.006%

    No Known Activations