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

    Neuronpedia

    INDEX
    Explanations

    dates

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    SPONSORED
    -0.80
     matters
    -0.79
    iments
    -0.75
    Joined
    -0.74
     furthermore
    -0.74
     suppose
    -0.73
     besides
    -0.72
     qualifies
    -0.71
     tempted
    -0.71
     deployments
    -0.70
    POSITIVE LOGITS
    atre
    0.84
     Golden
    0.79
     Butterfly
    0.78
    ©¶æ¥µ
    0.76
    ocratic
    0.75
     "#
    0.74
     Handbook
    0.74
     largest
    0.74
     Apprentice
    0.73
     Dalai
    0.72
    Act Density 0.197%

    No Known Activations