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

    Neuronpedia

    INDEX
    Explanations

    locations or regions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    xb
    -0.72
    oret
    -0.69
    atorium
    -0.69
    orem
    -0.69
    asma
    -0.68
    ãĥ£
    -0.68
    emaker
    -0.66
    ienne
    -0.66
    xe
    -0.66
    opic
    -0.66
    POSITIVE LOGITS
     respectively
    2.39
    depending
    1.32
     alike
    1.26
     depending
    1.13
     etc
    1.08
    etc
    1.01
     whichever
    1.00
     among
    0.95
     totaling
    0.92
     plus
    0.90
    Act Density 0.512%

    No Known Activations