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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating examples or comparisons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    á»IJ
    -0.17
    chet
    -0.15
    /goto
    -0.15
    даÑı
    -0.14
    ÙģÙĩÙĪÙħ
    -0.14
     Affero
    -0.14
    åĩºåĵģ
    -0.14
    thers
    -0.14
     Hüs
    -0.13
    kus
    -0.13
    POSITIVE LOGITS
     following
    0.29
     seguint
    0.26
    :↵
    0.24
    以ä¸ĭ
    0.23
    following
    0.22
    å¦Ĥä¸ĭ
    0.21
     Following
    0.21
     ÑģледÑĥÑİÑī
    0.21
    Following
    0.20
     ëĭ¤ìĿĮê³¼
    0.20
    Act Density 0.084%

    No Known Activations