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

    Neuronpedia

    INDEX
    Explanations

    names of individuals or characters

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names of people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     corrid
    -0.61
    ccording
    -0.61
     carbohyd
    -0.60
     polar
    -0.54
     millenn
    -0.53
    PDATE
    -0.51
     cryst
    -0.51
     exha
    -0.51
     polarization
    -0.51
     mobilization
    -0.50
    POSITIVE LOGITS
     Jr
    1.09
     III
    0.89
    ieri
    0.83
    ius
    0.78
    berger
    0.78
    iere
    0.77
    hoff
    0.75
    hart
    0.73
    iewicz
    0.73
    tein
    0.72
    Act Density 0.310%

    No Known Activations