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

    Neuronpedia

    INDEX
    Explanations

    information related to physical measurements and financial figures

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    asso
    -0.69
    æĦ
    -0.64
    odox
    -0.63
     causation
    -0.62
    çĶ°
    -0.62
    tnc
    -0.62
    nu
    -0.61
    Planet
    -0.57
    ãĤ´ãĥ³
    -0.57
    hod
    -0.56
    POSITIVE LOGITS
     total
    1.18
     apiece
    1.04
    total
    0.95
     annually
    0.93
    illion
    0.85
     TOTAL
    0.82
     crammed
    0.80
     respectively
    0.79
     compared
    0.79
     each
    0.74
    Act Density 3.708%

    No Known Activations