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

    Neuronpedia

    INDEX
    Explanations

    words related to pretentious or false behavior

    oai_token-act-pair · gpt-3.5-turbo

    words related to pretense or superficiality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     "$:/
    -0.66
     Pulse
    -0.66
    20439
    -0.65
    hower
    -0.64
     Slide
    -0.64
    stocks
    -0.63
     watershed
    -0.58
     Ferry
    -0.57
    tips
    -0.57
    SHIP
    -0.57
    POSITIVE LOGITS
    entious
    1.52
    ensions
    1.51
    ension
    1.42
    reatment
    1.30
    zel
    1.29
    ense
    1.20
    inent
    1.19
    reated
    1.15
    enses
    1.15
    reating
    1.15
    Act Density 0.018%

    No Known Activations