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

    Neuronpedia

    INDEX
    Explanations

    phrases related to different treatment or perspectives

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "differently" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Encyclopedia
    -0.73
    /+
    -0.66
    ELY
    -0.66
     Dmitry
    -0.64
     O
    -0.63
    advertising
    -0.62
    eer
    -0.60
     Zion
    -0.59
    bern
    -0.59
    á
    -0.59
    POSITIVE LOGITS
    iating
    1.07
    iator
    0.92
    iates
    0.90
    colored
    0.88
    wcs
    0.86
    psey
    0.85
     coloured
    0.83
    etheless
    0.82
     situated
    0.80
     colored
    0.79
    Act Density 0.006%

    No Known Activations