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

    Neuronpedia

    INDEX
    Explanations

    instances of single quotation marks and certain phrases related to speech or dialogue

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    els
    -0.15
    dorf
    -0.14
    iseum
    -0.14
    ÑģÑİ
    -0.14
    elta
    -0.13
     forthcoming
    -0.13
    cio
    -0.13
     “
    -0.13
    oyer
    -0.13
    opia
    -0.13
    POSITIVE LOGITS
    );$
    0.21
     dedim
    0.17
     frameborder
    0.17
    KANJI
    0.16
    Âĺ
    0.16
    },{"
    0.15
    068
    0.15
    Ë
    0.15
    -toast
    0.14
    GMEM
    0.14
    Act Density 0.157%

    No Known Activations