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

    Neuronpedia

    INDEX
    Explanations

    references to art and artists

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     htt
    -0.71
    士
    -0.61
     sclerosis
    -0.57
    ishable
    -0.55
     Contra
    -0.55
     Telecommunications
    -0.54
    CVE
    -0.54
     deter
    -0.54
     Plain
    -0.53
     overse
    -0.53
    POSITIVE LOGITS
    ificial
    1.64
    ifacts
    1.52
    icles
    1.49
    illery
    1.47
    ifact
    1.46
    isan
    1.43
    isans
    1.26
    istical
    1.22
    emis
    1.21
    ific
    1.21
    Act Density 0.028%

    No Known Activations