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

    proper nouns, specifically names of individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ablishment
    -0.75
    acebook
    -0.71
    undai
    -0.69
    ournal
    -0.69
    ossier
    -0.68
    ccording
    -0.68
    ggle
    -0.68
    LEASE
    -0.67
     referen
    -0.66
    alach
    -0.65
    POSITIVE LOGITS
     Jr
    1.07
     III
    1.05
    gren
    0.91
    gaard
    0.89
     aka
    0.87
     QC
    0.84
    etti
    0.83
     (@
    0.82
    berg
    0.81
    quist
    0.79
    Act Density 0.204%

    No Known Activations