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

    Neuronpedia

    INDEX
    Explanations

    information related to financial transactions, donations, and investments

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     Divinity
    -0.69
     strugg
    -0.67
     wors
    -0.63
     professions
    -0.62
     passer
    -0.59
     profession
    -0.58
     quot
    -0.58
     birthplace
    -0.58
     heights
    -0.58
     horizon
    -0.58
    POSITIVE LOGITS
    %%
    0.89
    USD
    0.85
    ½
    0.78
     apiece
    0.76
     USD
    0.75
    udos
    0.73
     yuan
    0.71
    -$
    0.71
    +
    0.68
    plus
    0.66
    Act Density 14.186%

    No Known Activations