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

    Neuronpedia

    INDEX
    Explanations

    references to software releases or updates

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    llan
    -0.70
    isma
    -0.69
    pn
    -0.68
    atomic
    -0.65
    fine
    -0.65
    akia
    -0.65
    GO
    -0.64
    atem
    -0.63
    pill
    -0.63
    sis
    -0.62
    POSITIVE LOGITS
    lisher
    0.89
    quished
    0.86
     announcements
    0.85
    tion
    0.82
    date
    0.81
     date
    0.77
    dates
    0.76
     RELE
    0.75
     Date
    0.73
     releasing
    0.73
    Act Density 2.010%

    No Known Activations