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

    Neuronpedia

    INDEX
    Explanations

    special characters used as symbols or markers in a text

    oai_token-act-pair · gpt-3.5-turbo

    the presence of non-standard characters or symbols in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Sic
    -0.66
     Western
    -0.65
     Libyan
    -0.64
     VICE
    -0.64
     retreat
    -0.63
     cellphone
    -0.63
    NRS
    -0.62
     Fou
    -0.62
     scatter
    -0.62
     guiActiveUnfocused
    -0.62
    POSITIVE LOGITS
    ¬
    1.17
    º
    1.07
    ¡
    1.07
    ¹
    1.03
    į
    0.97
    »
    0.95
    £
    0.95
    §
    0.93
    ĵ
    0.93
    ename
    0.92
    Act Density 0.580%

    No Known Activations