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

    Neuronpedia

    INDEX
    Explanations

    HTML tags

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     flourishing
    -0.74
     mushroom
    -0.72
     thous
    -0.72
     manif
    -0.71
     scattering
    -0.71
     incent
    -0.70
    seless
    -0.69
     administ
    -0.69
     recalling
    -0.68
     glim
    -0.67
    POSITIVE LOGITS
     âĢº
    0.88
    Temperature
    0.88
    °
    0.88
    âĶģ
    0.85
    Family
    0.85
    é¾į
    0.85
    MpServer
    0.82
    Enlarge
    0.82
    align
    0.82
    ef
    0.82
    Act Density 0.080%

    No Known Activations