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

    Neuronpedia

    INDEX
    Explanations

    terms related to legal matters and regulatory standards

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     reper
    -0.63
    Downloadha
    -0.61
     Âł Âł Âł Âł
    -0.60
     brim
    -0.59
    WAYS
    -0.55
    GAME
    -0.54
     adv
    -0.53
    PLE
    -0.52
     tac
    -0.52
    âĺħâĺħ
    -0.51
    POSITIVE LOGITS
    ing
    2.05
    ed
    1.91
    ation
    1.65
    edIn
    1.63
    ally
    1.53
    ary
    1.51
    ated
    1.48
    arily
    1.46
    edly
    1.44
    aries
    1.39
    Act Density 7.643%

    No Known Activations