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

    Neuronpedia

    INDEX
    Explanations

    names of political figures

    oai_token-act-pair · gpt-3.5-turbo

    names of notable public figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    The second or later name in a list of names, usually linked by "and" or "or"

    Explanation Uploaded by User
    New Auto-Interp
    Negative Logits
    adobe
    -0.77
     Lithuan
    -0.66
    effic
    -0.61
    /
    -0.61
    growth
    -0.57
    Requ
    -0.57
     NON
    -0.55
    ï¸
    -0.54
     RIS
    -0.53
     Latter
    -0.53
    POSITIVE LOGITS
     alike
    1.65
     respectively
    1.46
     together
    0.96
     jointly
    0.84
    mates
    0.77
    olson
    0.77
     combined
    0.75
    kefeller
    0.74
     collide
    0.74
     mutually
    0.74
    Act Density 0.322%

    No Known Activations