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

    Neuronpedia

    INDEX
    Explanations

    phrases related to political ideologies and policies

    oai_token-act-pair · gpt-3.5-turbo

    the usage of the indefinite article "a" in various contexts, particularly regarding societal concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Orig
    -0.83
    mates
    -0.77
    ESPN
    -0.74
     assignments
    -0.72
    videos
    -0.72
    grounds
    -0.71
     Annotations
    -0.70
    ographs
    -0.70
    arsity
    -0.69
    Contents
    -0.69
    POSITIVE LOGITS
    usterity
    1.33
     resurg
    1.04
     unified
    0.96
     nation
    0.95
     handful
    0.94
     trillion
    0.94
     plethora
    0.94
     totalitarian
    0.94
     comprehensive
    0.94
     balanced
    0.92
    Act Density 0.263%

    No Known Activations