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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of being "on" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    olina
    -0.17
    pus
    -0.16
    chsel
    -0.15
    olio
    -0.15
    cht
    -0.14
    sep
    -0.14
    itures
    -0.14
     eser
    -0.14
    anie
    -0.14
    Runnable
    -0.14
    POSITIVE LOGITS
     duty
    0.29
     leave
    0.28
     assignment
    0.24
    leave
    0.21
    -duty
    0.20
    assignment
    0.20
     jury
    0.19
     strike
    0.19
     Leave
    0.19
     holiday
    0.18
    Act Density 0.104%

    No Known Activations