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

    Neuronpedia

    INDEX
    Explanations

    references to charitable organizations and foundations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    TINGS
    -0.17
    reff
    -0.17
    sÃŃ
    -0.17
    TING
    -0.16
    ormsg
    -0.15
    338
    -0.15
    geh
    -0.15
    .REQUEST
    -0.14
    ern
    -0.14
    tings
    -0.14
    POSITIVE LOGITS
    /Foundation
    0.21
    stant
    0.17
     же
    0.17
    lation
    0.17
    ÑģÑĮ
    0.15
     Watts
    0.15
    lay
    0.15
    most
    0.14
    lated
    0.14
     impro
    0.14
    Act Density 0.025%

    No Known Activations