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

    Neuronpedia

    INDEX
    Explanations

    references to exploitation and labor systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    urre
    -0.14
    itore
    -0.14
    finity
    -0.14
    URRE
    -0.14
    ẹp
    -0.14
    _tac
    -0.14
    irsch
    -0.13
    ABA
    -0.13
     )↵↵↵↵↵↵↵↵
    -0.13
    yaw
    -0.13
    POSITIVE LOGITS
     labor
    0.44
     labour
    0.43
     work
    0.40
     Labor
    0.34
     Work
    0.32
     Labour
    0.31
     manual
    0.29
    Work
    0.28
    work
    0.28
    åĬ³
    0.28
    Act Density 0.180%

    No Known Activations