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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "work" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arel
    -0.21
    ouro
    -0.17
    acco
    -0.15
    imei
    -0.15
    Wr
    -0.14
    icha
    -0.14
     Wr
    -0.14
    ilities
    -0.14
    ELLOW
    -0.14
    anst
    -0.14
    POSITIVE LOGITS
     closely
    0.29
     directly
    0.21
     alongside
    0.19
     HAND
    0.18
     hands
    0.18
     withd
    0.17
     hand
    0.17
    à¹Īวมà¸ģ
    0.17
     side
    0.17
    _MI
    0.16
    Act Density 0.045%

    No Known Activations