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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "work" and its variants, indicating a focus on the concept of work or labor-related contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    clid
    -0.17
    592
    -0.16
    e
    -0.16
    urge
    -0.15
    irm
    -0.15
    lor
    -0.14
    mot
    -0.14
    quires
    -0.14
    thal
    -0.14
    ERCHANT
    -0.14
    POSITIVE LOGITS
    ktop
    0.19
    Ãłnh
    0.18
    INGTON
    0.18
    hest
    0.18
    wart
    0.17
    ombat
    0.16
    ingga
    0.16
    akit
    0.15
    robe
    0.15
    าย
    0.15
    Act Density 0.011%

    No Known Activations