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

    Neuronpedia

    INDEX
    Explanations

    names of notable individuals

    oai_token-act-pair · gpt-3.5-turbo

    names of individuals and associated influences or roles in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    į
    -0.68
     policeman
    -0.66
    gered
    -0.64
    wcs
    -0.63
    lehem
    -0.63
     Rarity
    -0.60
    urtles
    -0.59
    iliated
    -0.57
     srfAttach
    -0.57
    adier
    -0.57
    POSITIVE LOGITS
     personally
    0.75
    's
    0.74
    ÃŃs
    0.65
     Productions
    0.62
     experien
    0.61
    senal
    0.61
    aer
    0.61
     firsthand
    0.59
     presidency
    0.57
     Labs
    0.56
    Act Density 0.521%

    No Known Activations