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

    Neuronpedia

    INDEX
    Explanations

    phrases related to authority figures and their actions or roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     unfolded
    -0.15
     Woo
    -0.15
    ond
    -0.14
    ahr
    -0.14
     Operators
    -0.14
    angel
    -0.13
    arning
    -0.13
    ein
    -0.13
     Uncomment
    -0.13
    iox
    -0.13
    POSITIVE LOGITS
     office
    0.60
     OFF
    0.55
    office
    0.51
    _Off
    0.51
    -office
    0.49
     Office
    0.47
    OFF
    0.47
     offic
    0.46
    Off
    0.46
     offices
    0.45
    Act Density 0.120%

    No Known Activations