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

    Neuronpedia

    INDEX
    Explanations

    terms related to politics and social issues

    oai_token-act-pair · gpt-3.5-turbo

    words related to criticism and skepticism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĸļ
    -0.86
    andel
    -0.72
     DRAG
    -0.70
    erity
    -0.69
    angan
    -0.68
    aurus
    -0.66
    peed
    -0.65
    ecause
    -0.63
    omething
    -0.63
     proport
    -0.62
    POSITIVE LOGITS
    hood
    1.20
    ism
    1.00
    gery
    0.93
    ishly
    0.93
    doms
    0.92
    dom
    0.92
    ry
    0.91
    ship
    0.91
    isms
    0.90
    esses
    0.85
    Act Density 0.232%

    No Known Activations