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

    Neuronpedia

    INDEX
    Explanations

    phrases related to personal experiences or introspection

    oai_token-act-pair · gpt-3.5-turbo

    references to personal experiences and changes in one's life

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ey
    -0.77
    ERC
    -0.76
    mented
    -0.75
    atchewan
    -0.75
    essee
    -0.74
     Cosponsors
    -0.72
    IUM
    -0.72
    uggest
    -0.72
    ioxide
    -0.72
    ulic
    -0.72
    POSITIVE LOGITS
     expectancy
    1.18
    guards
    0.94
    scape
    0.89
    blood
    0.88
    guard
    0.88
     revolves
    0.86
    span
    0.83
    stem
    0.80
    mares
    0.80
     sciences
    0.76
    Act Density 0.043%

    No Known Activations