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

    Neuronpedia

    INDEX
    Explanations

    expressions of authenticity and genuine emotions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /TT
    -0.16
    sel
    -0.15
    ر
    -0.15
    sk
    -0.15
    ses
    -0.15
    side
    -0.15
    خاÙĨÙĩ
    -0.15
    sg
    -0.15
    sal
    -0.15
    (IT
    -0.15
    POSITIVE LOGITS
     effort
    0.20
    /auth
    0.20
    ably
    0.18
    -looking
    0.18
    -article
    0.17
    ity
    0.17
    imately
    0.17
     interest
    0.16
    amate
    0.16
    hend
    0.16
    Act Density 0.014%

    No Known Activations