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

    Neuronpedia

    INDEX
    Explanations

    keywords related to health, safety, and regulation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aeda
    -0.16
    amac
    -0.14
    oline
    -0.13
    纳
    -0.13
     å¤
    -0.13
    еп
    -0.13
    569
    -0.12
    locs
    -0.12
    ober
    -0.12
    __
    -0.12
    POSITIVE LOGITS
    åıĬåħ¶
    0.22
     ÙĪÙħا
    0.19
     вообÑīе
    0.16
    -vs
    0.15
    afil
    0.15
     Ñģамом
    0.15
     being
    0.15
    pecific
    0.14
     upcoming
    0.14
    _specific
    0.14
    Act Density 0.392%

    No Known Activations