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
     unmute
    -0.94
     dignité
    -0.90
     Enfield
    -0.89
    zbęd
    -0.87
     MainAxisSize
    -0.86
    quelize
    -0.82
    principalColumn
    -0.79
     deportivos
    -0.78
     Cessna
    -0.77
    guiente
    -0.77
    POSITIVE LOGITS
     worked
    1.56
     working
    1.56
     Worked
    1.43
    Working
    1.42
     Working
    1.40
    Worked
    1.35
     works
    1.34
     WORKING
    1.32
    worked
    1.30
    working
    1.25
    Act Density 0.076%

    No Known Activations