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

    Neuronpedia

    INDEX
    Explanations

    positions or titles of authority, such as ranks or job positions

    oai_token-act-pair · gpt-3.5-turbo

    phrases containing the word "of" related to various titles and positions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    NetMessage
    -0.81
     pieces
    -0.75
    NULL
    -0.74
     tantal
    -0.72
     gaps
    -0.72
     flashbacks
    -0.71
     assumptions
    -0.70
     misconceptions
    -0.68
    boats
    -0.67
     rive
    -0.67
    POSITIVE LOGITS
    united
    0.85
     Nations
    0.83
     Legislative
    0.75
     State
    0.74
     Duty
    0.74
     Greater
    0.73
     Parliament
    0.73
     Operations
    0.72
     Engineers
    0.71
     National
    0.71
    Act Density 0.185%

    No Known Activations