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

    Neuronpedia

    INDEX
    Explanations

    phrases related to lists and citations

    oai_token-act-pair · gpt-3.5-turbo

    the presence of closing square brackets and associated numerical references in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ń·
    -0.75
    onite
    -0.72
    oe
    -0.71
    ciating
    -0.69
     unwanted
    -0.68
    Copyright
    -0.65
    Msg
    -0.60
    OX
    -0.60
    alore
    -0.60
    ĵĺ
    -0.59
    POSITIVE LOGITS
    *.
    0.68
    enegger
    0.67
    eous
    0.67
    dfx
    0.67
    âĨij
    0.66
     onwards
    0.65
    TPS
    0.63
     Ibid
    0.63
    sbm
    0.62
     notably
    0.62
    Act Density 0.042%

    No Known Activations