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

    Neuronpedia

    INDEX
    Explanations

    phrases related to socio-economic issues and education

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rof
    -0.15
    è¼Ķ
    -0.15
    uries
    -0.15
     roÄįnÃŃ
    -0.15
     Fool
    -0.14
     Ethics
    -0.14
    _unused
    -0.14
    \brief
    -0.14
    ueur
    -0.14
     zel
    -0.14
    POSITIVE LOGITS
     labour
    0.26
     earnings
    0.23
     labor
    0.23
    earn
    0.23
     Labour
    0.21
    Labour
    0.19
     decom
    0.19
    Specification
    0.19
     Decom
    0.18
     Labor
    0.17
    Act Density 0.038%

    No Known Activations