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

    Neuronpedia

    INDEX
    Explanations

    terms related to legislative or regulatory language

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ulin
    -0.15
    gren
    -0.15
    uli
    -0.15
    вий
    -0.14
    oint
    -0.14
    loe
    -0.13
    lich
    -0.13
    ollapse
    -0.13
    _defaults
    -0.13
    gth
    -0.13
    POSITIVE LOGITS
     elev
    0.15
    amat
    0.14
    ãģªãĤĵãģ¦
    0.14
     Gallagher
    0.14
     âĢ
    0.14
    rip
    0.14
    arti
    0.13
    erton
    0.13
    aptive
    0.13
    acle
    0.13
    Act Density 0.077%

    No Known Activations