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

    Neuronpedia

    INDEX
    Explanations

    high-profile individuals or events

    oai_token-act-pair · gpt-3.5-turbo

    references to high-profile individuals or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aves
    -0.73
    uits
    -0.70
    iph
    -0.68
    shall
    -0.67
    iphany
    -0.67
    otent
    -0.66
    ope
    -0.65
    AUT
    -0.63
    ajor
    -0.62
    sis
    -0.62
    POSITIVE LOGITS
     celebrity
    0.84
     bearer
    0.77
     endorsements
    0.76
     contender
    0.74
     assassination
    0.74
    clinton
    0.73
     assass
    0.70
    profile
    0.70
     accomplishments
    0.67
     celebrities
    0.66
    Act Density 0.016%

    No Known Activations