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

    Neuronpedia

    INDEX
    Explanations

    blocks of comment code in programming languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ion
    -0.17
    atern
    -0.15
    uber
    -0.14
    oro
    -0.14
     fairness
    -0.14
    kees
    -0.13
    殿
    -0.13
    oints
    -0.13
    nd
    -0.13
     oy
    -0.13
    POSITIVE LOGITS
    ØŃاد
    0.15
    Ïħμ
    0.15
     Maz
    0.15
    abee
    0.15
    agara
    0.15
    alic
    0.15
    HttpException
    0.14
    itzer
    0.14
    prite
    0.14
    elic
    0.14
    Act Density 0.046%

    No Known Activations