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

    Neuronpedia

    INDEX
    Explanations

    names of individuals

    oai_token-act-pair · gpt-3.5-turbo

    phrases that are directly related to notable people or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pport
    -0.75
    pled
    -0.66
    alities
    -0.65
    antic
    -0.64
    rule
    -0.63
    osc
    -0.63
     cues
    -0.63
    ocry
    -0.62
    ologies
    -0.62
    raq
    -0.61
    POSITIVE LOGITS
     Jr
    1.23
     aka
    1.09
     PhD
    1.03
     Sr
    1.00
     MD
    0.98
    Jr
    0.96
     founder
    0.89
     formerly
    0.89
     Founder
    0.86
     Contribut
    0.84
    Act Density 0.131%

    No Known Activations