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

    Neuronpedia

    INDEX
    Explanations

    particular words such as "proper" and terms related to measurements and specifications

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    _>
    -0.69
    hyde
    -0.69
    âĹı
    -0.66
     Lilly
    -0.64
    acid
    -0.62
    è¦ļéĨĴ
    -0.62
    yrs
    -0.61
    =-=-=-=-
    -0.60
     ank
    -0.60
    ³³³³³³³³³³³³³³³³
    -0.59
    POSITIVE LOGITS
    tarian
    1.19
     functioning
    0.98
    tarians
    0.85
     noun
    0.84
    bred
    0.80
     etiquette
    0.75
    nsic
    0.75
     guiActiveUn
    0.73
    lly
    0.71
    iciary
    0.70
    Act Density 9.107%

    No Known Activations