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

    Neuronpedia

    INDEX
    Explanations

    direct speech phrases containing the word "said."

    oai_token-act-pair · gpt-3.5-turbo

    instances of reported speech or quotations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Pont
    -0.86
    tumblr
    -0.77
    otype
    -0.73
    Quantity
    -0.72
    à¦
    -0.71
    icum
    -0.69
    NI
    -0.67
    pee
    -0.67
    Recipe
    -0.67
    EMBER
    -0.66
    POSITIVE LOGITS
     goodbye
    0.83
     moreover
    0.81
    :"
    0.76
     furthermore
    0.74
     anecd
    0.69
     bluntly
    0.68
     sarcast
    0.66
     secondly
    0.65
    :]
    0.64
     afterwards
    0.63
    Act Density 0.216%

    No Known Activations