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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating worthiness or deservingness

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    ullivan
    -0.57
    glers
    -0.53
     synchronized
    -0.51
    nels
    -0.50
     interstate
    -0.48
     portals
    -0.47
    lems
    -0.47
     processes
    -0.46
    uthor
    -0.46
     surfing
    -0.46
    POSITIVE LOGITS
     praise
    0.65
     scorn
    0.61
     ridicule
    0.58
    $$$$
    0.55
    COMPLE
    0.55
     criticism
    0.54
    cipled
    0.54
    cellence
    0.54
    inement
    0.53
    ortality
    0.53
    Act Density 11.477%

    No Known Activations