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

    Neuronpedia

    INDEX
    Explanations

    titles of songs, tv shows, and movies

    oai_token-act-pair · gpt-3.5-turbo

    quotation marks and their associated content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    etheless
    -0.89
    bris
    -0.85
    MpServer
    -0.78
    ngth
    -0.77
    İĭ
    -0.76
    qqa
    -0.75
    agn
    -0.74
    »Ĵ
    -0.74
     pulp
    -0.73
    ĻĤ
    -0.73
    POSITIVE LOGITS
     redirect
    0.91
    /"
    0.74
     refers
    0.71
    ãģ®
    0.70
     translates
    0.70
     Refugees
    0.68
     reads
    0.67
     Jaguars
    0.66
     Democracy
    0.65
     Desert
    0.65
    Act Density 0.095%

    No Known Activations