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

    Neuronpedia

    INDEX
    Explanations

    phrases related to transformation or change

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    erity
    -0.73
    inately
    -0.69
    ongyang
    -0.67
     Cran
    -0.64
     travelled
    -0.64
    !/
    -0.63
    merga
    -0.59
    bell
    -0.59
    WARE
    -0.59
    pressure
    -0.58
    POSITIVE LOGITS
     adulthood
    0.88
     extinct
    0.88
     insign
    0.78
     usable
    0.77
     unman
    0.76
     permanent
    0.76
     indistinguishable
    0.74
     increasingly
    0.72
     anew
    0.72
     profitable
    0.71
    Act Density 4.349%

    No Known Activations