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

    Neuronpedia

    INDEX
    Explanations

    requests, recommendations, and information in an online context

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     Thrones
    -0.79
     Stones
    -0.77
     Corps
    -0.73
     Mississ
    -0.73
     Canaver
    -0.72
     Legions
    -0.69
     Schwar
    -0.69
     Okin
    -0.68
     Grail
    -0.68
     Scheme
    -0.67
    POSITIVE LOGITS
    terday
    1.01
    etheless
    0.91
    ande
    0.86
    @
    0.84
    theless
    0.84
    _
    0.82
    ickr
    0.82
    anwhile
    0.82
    maxwell
    0.78
     guiActiveUn
    0.76
    Act Density 0.461%

    No Known Activations