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

    Neuronpedia

    INDEX
    Explanations

    words related to playful or mocking interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anh
    -0.19
    jac
    -0.15
    iani
    -0.15
    vr
    -0.15
    ainment
    -0.15
    è¢ĭ
    -0.14
    reon
    -0.14
    anton
    -0.14
    ko
    -0.14
    аÑĦ
    -0.14
    POSITIVE LOGITS
    isclosed
    0.15
    mploy
    0.15
     Byl
    0.15
    lemn
    0.15
    modo
    0.15
    upy
    0.14
    Å¡ÃŃm
    0.14
    uncio
    0.14
    peria
    0.14
    rieg
    0.14
    Act Density 0.006%

    No Known Activations