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

    Neuronpedia

    INDEX
    Explanations

    phrases related to military or tactical operations

    oai_token-act-pair · gpt-3.5-turbo

    terms related to law enforcement and investigative activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    )?
    -0.69
    inas
    -0.64
     Conclusion
    -0.63
     tongues
    -0.63
     minorities
    -0.62
    comments
    -0.61
    },"
    -0.60
     Videos
    -0.60
     Issues
    -0.60
     Retrieved
    -0.59
    POSITIVE LOGITS
     consisting
    1.05
     containing
    0.83
     comprising
    0.77
     intending
    0.77
     resembling
    0.75
     onto
    0.74
     named
    0.71
     into
    0.70
     totaling
    0.70
     called
    0.70
    Act Density 0.518%

    No Known Activations