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

    Neuronpedia

    INDEX
    Explanations

    information about significant or impactful events

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     Flavoring
    -0.82
     corners
    -0.79
     Abilities
    -0.73
    know
    -0.71
    uld
    -0.71
    aths
    -0.67
    essor
    -0.66
     Practices
    -0.64
    idents
    -0.63
    ways
    -0.63
    POSITIVE LOGITS
     aimed
    1.05
     intended
    0.97
     reminiscent
    0.93
     reproduced
    0.88
     titled
    0.87
     moot
    0.86
     straightforward
    0.86
     summarized
    0.85
     forwarded
    0.83
     reprinted
    0.83
    Act Density 1.749%

    No Known Activations