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

    Neuronpedia

    INDEX
    Explanations

    instances where someone is pretending or plays a role

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to pretending and personal identity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    owder
    -0.71
    arton
    -0.67
    ousand
    -0.67
    arian
    -0.67
    cember
    -0.66
    zb
    -0.65
    mentioned
    -0.65
    olla
    -0.64
    atl
    -0.64
    "]=>
    -0.64
    POSITIVE LOGITS
     invincible
    1.13
     infall
    0.96
     superiority
    0.87
     inferior
    0.87
     unbeat
    0.83
     omnip
    0.76
     immutable
    0.76
     innocence
    0.74
     nonexistent
    0.74
     benevolent
    0.73
    Act Density 0.332%

    No Known Activations