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

    Neuronpedia

    INDEX
    Explanations

    words related to protests

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of protests and festivals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gap
    -0.70
    nesia
    -0.68
    bra
    -0.65
    forward
    -0.65
     splitting
    -0.63
    space
    -0.63
    brain
    -0.62
     stable
    -0.62
    smart
    -0.61
    planes
    -0.61
    POSITIVE LOGITS
    ests
    1.26
    imony
    1.04
    iqu
    0.94
    icism
    0.92
    iques
    0.85
    osterone
    0.84
    ongs
    0.83
    icult
    0.83
    imates
    0.82
    icist
    0.82
    Act Density 0.011%

    No Known Activations