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

    Neuronpedia

    INDEX
    Explanations

    phrases related to political discourse

    oai_token-act-pair · gpt-3.5-turbo

    statements related to desperation and accountability in political or military contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     hatch
    -0.87
     hyd
    -0.79
     healer
    -0.74
     helper
    -0.72
    ributes
    -0.71
     mats
    -0.69
     beginner
    -0.68
     calf
    -0.68
     corrid
    -0.67
     mur
    -0.66
    POSITIVE LOGITS
     Hence
    1.19
     Moreover
    1.17
     Thus
    1.17
     Whereas
    1.15
     Flavoring
    1.15
     Therefore
    1.15
     Consequently
    1.14
     Indeed
    1.14
     Regardless
    1.11
     Nevertheless
    1.11
    Act Density 0.929%

    No Known Activations