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

    Neuronpedia

    INDEX
    Explanations

    concepts related to diversity and inclusion within communities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ero
    -0.19
    abl
    -0.14
     Certain
    -0.14
    è¼Ķ
    -0.14
    ierz
    -0.14
    oucher
    -0.14
    BackPressed
    -0.14
    lets
    -0.14
    oy
    -0.14
    ouz
    -0.13
    POSITIVE LOGITS
     everything
    0.30
    everything
    0.25
    :↵
    0.24
     Everything
    0.23
    :*
    0.23
    Everything
    0.22
    :
    0.20
    :č↵
    0.20
    :.
    0.18
     both
    0.18
    Act Density 0.088%

    No Known Activations