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

    Neuronpedia

    INDEX
    Explanations

    phrases or words related to amendments or changes

    oai_token-act-pair · gpt-3.5-turbo

    instances of the words "amend" and "amended."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    á
    -0.74
    zees
    -0.72
    gins
    -0.68
     Dolphins
    -0.65
     Bears
    -0.63
     Famous
    -0.63
     Ferry
    -0.63
     Flying
    -0.62
     Ft
    -0.62
     Tec
    -0.62
    POSITIVE LOGITS
    terday
    0.99
    ments
    0.86
    xual
    0.78
    amental
    0.76
    ements
    0.75
     misunder
    0.71
    mented
    0.69
    hap
    0.69
    ivid
    0.68
    mentation
    0.67
    Act Density 0.016%

    No Known Activations