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

    Neuronpedia

    INDEX
    Explanations

    references to pilot projects

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     Machina
    -0.80
    upon
    -0.78
    Else
    -0.75
    andra
    -0.72
    die
    -0.71
    roots
    -0.66
    ktop
    -0.66
     Extrem
    -0.66
    elo
    -0.65
     Lauder
    -0.65
    POSITIVE LOGITS
     pilot
    0.93
     episode
    0.88
    isode
    0.83
    wings
    0.79
    spective
    0.77
    ships
    0.76
     Pilot
    0.73
     project
    0.73
    matically
    0.72
     experiment
    0.72
    Act Density 0.014%

    No Known Activations