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

    Neuronpedia

    INDEX
    Explanations

    rare and exclusive items or achievements

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    ĸļ
    -0.58
     phil
    -0.56
     chem
    -0.56
     bom
    -0.55
     Zac
    -0.55
     jet
    -0.53
     Giul
    -0.52
     Castro
    -0.51
     Scrib
    -0.51
     tug
    -0.51
    POSITIVE LOGITS
    Uncommon
    0.87
    Rare
    0.85
    ersive
    0.71
    ãĥĪ
    0.66
    Common
    0.63
    TI
    0.63
    Recipe
    0.62
    Japanese
    0.61
    minster
    0.61
    Beta
    0.61
    Act Density 6.145%

    No Known Activations