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

    Neuronpedia

    INDEX
    Explanations

    phrases related to measurement and assessment

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    raid
    -0.88
    udeb
    -0.79
    sky
    -0.76
    ozy
    -0.75
    oing
    -0.75
    vous
    -0.72
    lez
    -0.71
    ici
    -0.69
    ski
    -0.68
    lishing
    -0.68
    POSITIVE LOGITS
     elapsed
    0.86
     measuring
    0.86
     measurement
    0.84
     distances
    0.82
     metrics
    0.77
     amount
    0.77
     measurements
    0.76
     scales
    0.74
     inacc
    0.73
     accuracy
    0.72
    Act Density 1.001%

    No Known Activations