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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to providing assistance, support, and care for others

    oai_token-act-pair · gpt-3.5-turbo

    actions related to influencing or controlling others

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    recorded
    -0.64
    ãĥ¼ãĥĨãĤ£
    -0.63
    vertisement
    -0.62
     teasp
    -0.61
    vertising
    -0.60
    ÃĥÃĤ
    -0.59
    ãĥ¼ãĥĨ
    -0.59
    ogg
    -0.59
    luster
    -0.57
    ÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤ
    -0.57
    POSITIVE LOGITS
     thee
    0.73
     yourselves
    0.71
     oneself
    0.70
    )?
    0.64
     alot
    0.63
     rapists
    0.62
     yourself
    0.62
     him
    0.62
     Rs
    0.61
     me
    0.59
    Act Density 0.849%

    No Known Activations