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

    Neuronpedia

    INDEX
    Explanations

    conditional statements or hypothetical scenarios

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     Flavoring
    -0.84
     Outbreak
    -0.78
    ORPG
    -0.78
    Domin
    -0.75
    IDER
    -0.69
    Hug
    -0.69
    edition
    -0.69
    anon
    -0.69
    vantage
    -0.68
    ergy
    -0.68
    POSITIVE LOGITS
     unintentionally
    0.85
     technically
    0.85
    yip
    0.84
     theoretically
    0.81
     they
    0.80
     remotely
    0.79
     inadvertently
    0.77
     SOME
    0.76
     admittedly
    0.74
     unwittingly
    0.74
    Act Density 11.536%

    No Known Activations