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

    Neuronpedia

    INDEX
    Explanations

    phrases related to ongoing or repeated actions

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    lights
    -0.82
    mares
    -0.81
    pu
    -0.81
    dt
    -0.78
    hog
    -0.78
    iewicz
    -0.78
    Tier
    -0.77
    flags
    -0.77
    sg
    -0.77
     Awakens
    -0.76
    POSITIVE LOGITS
    ggy
    0.90
    omething
    0.88
    pez
    0.87
     nothing
    0.84
     brisk
    0.84
    ored
    0.83
    berman
    0.81
     something
    0.81
    zed
    0.79
    omsday
    0.79
    Act Density 0.632%

    No Known Activations