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

    Neuronpedia

    INDEX
    Explanations

    specific references to significant entities and themes related to injustice and societal issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .tencent
    -0.16
     Sil
    -0.15
    cae
    -0.14
    à¸Ĺà¸Ńà¸ĩ
    -0.14
    ical
    -0.14
     Hanging
    -0.14
     pockets
    -0.14
     hangs
    -0.14
    lify
    -0.14
    Hang
    -0.14
    POSITIVE LOGITS
    adesh
    0.14
    avar
    0.14
    един
    0.14
    eti
    0.14
    моÑĢ
    0.14
    ario
    0.13
    umin
    0.13
    ettle
    0.13
    arat
    0.13
     singly
    0.13
    Act Density 0.034%

    No Known Activations