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

    Neuronpedia

    INDEX
    Explanations

    words related to specific countries or entities

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns and geographical locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    later
    -0.66
     Cerberus
    -0.62
    oldemort
    -0.61
     clot
    -0.61
    姫
    -0.56
    araoh
    -0.55
    ulhu
    -0.55
     Cosponsors
    -0.55
    anwhile
    -0.54
    fetched
    -0.53
    POSITIVE LOGITS
    Wiki
    0.65
    ®
    0.60
    Ê
    0.59
     catalogue
    0.59
    igon
    0.54
     experience
    0.54
     constitu
    0.52
    ivable
    0.51
     Distance
    0.51
     Wiki
    0.51
    Act Density 1.160%

    No Known Activations