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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating future actions or intentions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     will
    -0.21
    will
    -0.17
    æľĥ
    -0.16
    yn
    -0.15
     akan
    -0.15
     ÑģÑĤанеÑĤ
    -0.15
     бÑĥде
    -0.15
     WILL
    -0.14
    odash
    -0.14
    atta
    -0.14
    POSITIVE LOGITS
     notice
    0.18
    lush
    0.15
    ingly
    0.15
    dre
    0.15
    _notice
    0.15
    notice
    0.15
    áŁĴáŀ
    0.14
    amus
    0.14
    ingham
    0.14
     find
    0.14
    Act Density 0.064%

    No Known Activations