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

    Neuronpedia

    INDEX
    Explanations

    references to privacy or private matters

    oai_token-act-pair · gpt-3.5-turbo

    references to privacy or private matters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    annis
    -0.82
    addons
    -0.77
    xual
    -0.75
    BIL
    -0.75
    è¦ļéĨĴ
    -0.71
    awa
    -0.71
    ocalypse
    -0.70
    ologies
    -0.70
    rers
    -0.68
    Population
    -0.68
    POSITIVE LOGITS
     sector
    0.91
     equity
    0.87
     affairs
    0.79
    ised
    0.73
    mouth
    0.72
     investigator
    0.72
     opinion
    0.72
     rented
    0.71
     ownership
    0.70
     conversations
    0.68
    Act Density 0.018%

    No Known Activations