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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal and political matters

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of sentences, particularly those relating to political topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     glim
    -0.85
     uncommon
    -0.78
     healer
    -0.78
     handmade
    -0.78
     helper
    -0.77
     workspace
    -0.77
     challeng
    -0.76
     hatch
    -0.76
     quir
    -0.75
     disemb
    -0.75
    POSITIVE LOGITS
     Worse
    1.48
     Meanwhile
    1.35
     Ironically
    1.30
     Needless
    1.28
     Thus
    1.21
     Moreover
    1.20
     Apparently
    1.20
     Hence
    1.18
     Surely
    1.15
     Shame
    1.15
    Act Density 0.513%

    No Known Activations