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

    Neuronpedia

    INDEX
    Explanations

    phrases related to expressing opinions or perspectives

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the word "with" in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Awakens
    -0.67
    bilt
    -0.62
    shire
    -0.60
     slump
    -0.58
    sylvania
    -0.58
     Basics
    -0.56
    hood
    -0.56
     unemploy
    -0.55
    pad
    -0.54
    mAh
    -0.54
    POSITIVE LOGITS
     regard
    1.52
     regards
    1.41
    stood
    1.38
    draw
    1.36
    drawn
    1.27
     respect
    1.26
     impunity
    1.15
    standing
    1.06
    holding
    0.93
     utmost
    0.86
    Act Density 0.201%

    No Known Activations