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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to political figures and government organizations

    oai_token-act-pair · gpt-3.5-turbo

    instances of statements or quotes made by individuals or authorities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    otin
    -0.90
     ILCS
    -0.86
    à¦
    -0.86
    =~=~
    -0.80
    RH
    -0.75
    COR
    -0.69
    VIDEO
    -0.68
    physical
    -0.68
    Exit
    -0.67
    ï¸
    -0.66
    POSITIVE LOGITS
    doms
    0.95
     bluntly
    0.88
     goodbye
    0.81
     sarcast
    0.79
     afterward
    0.75
     afterwards
    0.72
     anecd
    0.72
     emphatically
    0.71
     aloud
    0.68
     repeatedly
    0.66
    Act Density 0.279%

    No Known Activations