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

    Neuronpedia

    INDEX
    Explanations

    critics or opponents of various plans, policies, or actions

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals or groups who express opposition or criticism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Pradesh
    -0.70
     carnage
    -0.65
     Anniversary
    -0.65
    owship
    -0.63
     ingestion
    -0.62
     sunrise
    -0.61
     sunset
    -0.58
     bilateral
    -0.58
    ibrary
    -0.57
    UCK
    -0.57
    POSITIVE LOGITS
    paces
    1.19
    hip
    1.06
    oft
    0.98
    hesis
    0.98
     thereof
    0.97
    ervatives
    0.93
    hips
    0.89
    pace
    0.87
     argue
    0.85
     alike
    0.84
    Act Density 0.107%

    No Known Activations