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

    Neuronpedia

    INDEX
    Explanations

    words related to protests and activism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     needles
    -0.72
     noodles
    -0.69
    inia
    -0.69
     gorge
    -0.67
     ponds
    -0.63
     spears
    -0.63
     Cornell
    -0.62
    worms
    -0.62
    ieri
    -0.62
     swall
    -0.60
    POSITIVE LOGITS
    blems
    1.30
    gression
    1.22
    gressive
    1.21
    secut
    1.19
    ceed
    1.18
    posal
    1.16
    digy
    1.12
    secution
    1.07
    spect
    1.05
    hibited
    1.04
    Act Density 0.011%

    No Known Activations