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

    Neuronpedia

    INDEX
    Explanations

    names and surnames

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names and titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ambassadors
    -0.67
     envy
    -0.63
     apex
    -0.58
     alleg
    -0.58
     polar
    -0.58
     governors
    -0.57
     plates
    -0.55
     independents
    -0.55
     clubhouse
    -0.55
     Poles
    -0.55
    POSITIVE LOGITS
    ovich
    0.97
    chuk
    0.94
    itz
    0.94
     Jr
    0.93
    inski
    0.89
    owicz
    0.89
    auer
    0.87
    akis
    0.87
    ansky
    0.85
    owski
    0.85
    Act Density 0.398%

    No Known Activations