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

    Neuronpedia

    INDEX
    Explanations

    aspects related to features or elements of a system

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    ander
    -1.17
    verbs
    -1.07
    annis
    -1.06
    anders
    -1.04
    ESCO
    -1.02
    sil
    -1.01
    gently
    -0.99
    odore
    -0.97
    pta
    -0.96
    ricanes
    -0.93
    POSITIVE LOGITS
     thereof
    1.23
    ality
    1.14
    ial
    1.10
     aspects
    1.07
    ials
    1.04
     of
    1.03
     facets
    0.95
    ially
    0.90
    alities
    0.86
    iator
    0.86
    Act Density 0.444%

    No Known Activations