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

    Neuronpedia

    INDEX
    Explanations

    mathematical variables and symbolic expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anzi
    -0.15
    alama
    -0.15
    ahkan
    -0.14
    orpor
    -0.14
    ädchen
    -0.14
    ihan
    -0.14
    ologne
    -0.14
    $MESS
    -0.14
    agma
    -0.14
    ipple
    -0.13
    POSITIVE LOGITS
    431
    0.17
    889
    0.14
    µ
    0.14
    OTS
    0.14
    chat
    0.14
    ateria
    0.14
    ãĤ¹ãĥĨãĤ£
    0.13
    é«ĺæł¡
    0.13
    ander
    0.13
    436
    0.13
    Act Density 0.162%

    No Known Activations