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

    Neuronpedia

    INDEX
    Explanations

    quotes from various individuals

    oai_token-act-pair · gpt-3.5-turbo

    the repetition of the word "said" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    VIDEO
    -0.78
    physical
    -0.74
    otin
    -0.73
    spir
    -0.71
    respective
    -0.70
    à¦
    -0.70
    Holy
    -0.70
    otion
    -0.68
    =~=~
    -0.66
    WATCH
    -0.65
    POSITIVE LOGITS
    heit
    0.86
     goodbye
    0.85
     bluntly
    0.83
    doms
    0.82
     sarcast
    0.81
     afterward
    0.79
     aloud
    0.72
     afterwards
    0.70
     adam
    0.69
     emphatically
    0.68
    Act Density 0.229%

    No Known Activations