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

    Neuronpedia

    INDEX
    Explanations

    phrases related to social issues and criticisms

    oai_token-act-pair · gpt-3.5-turbo

    references to collective ownership or shared experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wrap
    -0.76
    wic
    -0.74
    puff
    -0.74
    bender
    -0.74
    ouse
    -0.72
    yang
    -0.72
     Levine
    -0.72
    AE
    -0.70
    icted
    -0.68
    zzle
    -0.68
    POSITIVE LOGITS
    selves
    1.30
     ancestors
    1.19
     nation
    1.18
     own
    1.17
     shores
    1.07
     selves
    1.05
     beloved
    1.05
     collective
    1.04
     country
    1.02
     society
    0.97
    Act Density 0.120%

    No Known Activations