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

    Neuronpedia

    INDEX
    Explanations

    discussions that involve conversations and social interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    imos
    -0.16
    linger
    -0.16
    emos
    -0.15
    otate
    -0.15
     Trap
    -0.15
    aille
    -0.14
     Pis
    -0.14
    ockey
    -0.14
     Shuffle
    -0.14
    Å¡lo
    -0.14
    POSITIVE LOGITS
    plitude
    0.16
    sage
    0.15
     Lad
    0.15
    errer
    0.15
    ÏĥÏĦαν
    0.14
     Wag
    0.14
    inka
    0.14
    ãĤ¹ãĥ¬
    0.14
    пов
    0.13
     yas
    0.13
    Act Density 0.006%

    No Known Activations