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

    Neuronpedia

    INDEX
    Explanations

    words related to specific person names, particularly "Jae."

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals and their roles or contributions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mie
    -0.82
    auld
    -0.78
    assium
    -0.75
     Cosponsors
    -0.74
    ivalent
    -0.71
    ified
    -0.70
    ion
    -0.68
    Unity
    -0.68
    roud
    -0.68
    Ó
    -0.68
    POSITIVE LOGITS
    gers
    0.86
    ger
    0.84
    xit
    0.80
    choes
    0.79
    ppel
    0.79
    gency
    0.77
    gel
    0.75
    vironment
    0.74
    velop
    0.71
    gling
    0.69
    Act Density 0.021%

    No Known Activations