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

    Neuronpedia

    INDEX
    Explanations

    words related to advocacy or support for a cause

    oai_token-act-pair · gpt-3.5-turbo

    terms related to pro-choice perspectives and advocacy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤ¼ãĤ¦ãĤ¹
    -0.83
     needles
    -0.79
     straw
    -0.70
     Halls
    -0.69
     Twain
    -0.69
     spears
    -0.69
     caves
    -0.69
     Brooks
    -0.68
     bedrooms
    -0.67
     ponds
    -0.66
    POSITIVE LOGITS
    digy
    1.34
    blems
    1.32
    ceed
    1.31
    secut
    1.24
    secution
    1.19
    posal
    1.18
    gression
    1.11
    spect
    1.10
    gressive
    1.09
    hibited
    1.07
    Act Density 0.017%

    No Known Activations