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

    Neuronpedia

    INDEX
    Explanations

    phrases related to discussing or mentioning something

    oai_token-act-pair · gpt-3.5-turbo

    the word "about" in various contexts related to discussions or topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ©¶æ¥µ
    -0.66
    strap
    -0.64
    Added
    -0.64
    sky
    -0.63
    Written
    -0.63
    falls
    -0.62
    HT
    -0.61
    waters
    -0.61
    quartered
    -0.61
    serv
    -0.61
    POSITIVE LOGITS
     how
    0.78
     reforming
    0.78
     topics
    0.74
     specifics
    0.72
     whether
    0.70
    eday
    0.70
     stopping
    0.69
     wanting
    0.68
     quitting
    0.68
    pheus
    0.66
    Act Density 0.071%

    No Known Activations