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

    Neuronpedia

    INDEX
    Explanations

    proper names of individuals

    oai_token-act-pair · gpt-3.5-turbo

    proper names, particularly political figures or notable individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    interstitial
    -0.92
    unity
    -0.78
    hement
    -0.77
    anchez
    -0.76
    essed
    -0.76
    ciating
    -0.76
    atl
    -0.75
    statement
    -0.74
    ichick
    -0.74
    eatures
    -0.74
    POSITIVE LOGITS
     Eh
    0.91
     Fein
    0.74
     Kant
    0.73
    lehem
    0.71
    lers
    0.70
     Dru
    0.70
    renheit
    0.70
     Strikes
    0.69
     Lans
    0.69
     Fro
    0.67
    Act Density 0.025%

    No Known Activations