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

    Neuronpedia

    INDEX
    Explanations

    terms related to law or legality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SHIP
    -0.76
    pty
    -0.71
    iotics
    -0.71
    ��
    -0.71
    sers
    -0.69
    igslist
    -0.69
    LOCK
    -0.67
    swer
    -0.62
     Annotations
    -0.62
    ryu
    -0.62
    POSITIVE LOGITS
    arer
    0.66
    ed
    0.65
    robe
    0.64
    partisan
    0.63
     accent
    0.59
    aed
    0.59
    erv
    0.59
    AAA
    0.58
    endra
    0.58
    ron
    0.58
    Act Density 1.411%

    No Known Activations