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

    Neuronpedia

    INDEX
    Explanations

    terms related to darkness and its various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    annon
    -0.16
    IMIZE
    -0.15
    zig
    -0.15
    .observable
    -0.14
    uv
    -0.14
    -bearing
    -0.14
    386
    -0.14
    alue
    -0.14
    trinsic
    -0.14
    iras
    -0.14
    POSITIVE LOGITS
    ened
    0.23
    ening
    0.20
    -dark
    0.18
    rd
    0.17
    sville
    0.16
    ness
    0.15
    itecture
    0.15
    lings
    0.15
    -bs
    0.15
    à¹Ģà¸ģà¸Ńร
    0.15
    Act Density 0.067%

    No Known Activations