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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating completion or actions being performed

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    weise
    -0.17
    .gs
    -0.16
    mania
    -0.15
    ship
    -0.15
    wig
    -0.14
    rang
    -0.14
    sun
    -0.14
    å§Ķåijĺ
    -0.14
    son
    -0.13
    worth
    -0.13
    POSITIVE LOGITS
    osed
    0.17
    pez
    0.16
    exterity
    0.15
    aling
    0.15
    ç¼
    0.15
    erness
    0.14
    etwork
    0.14
    ils
    0.14
    zw
    0.14
    ãĥ¼ãĥĨãĤ£
    0.14
    Act Density 0.064%

    No Known Activations