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

    Neuronpedia

    INDEX
    Explanations

    references to possessive pronouns (his, her) and associated information

    oai_token-act-pair · gpt-3.5-turbo

    the use of the word "or" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Novel
    -0.63
     lymph
    -0.57
    perture
    -0.57
     FINAL
    -0.56
     bree
    -0.54
    aven
    -0.54
     Ratings
    -0.53
     extensively
    -0.53
     Drift
    -0.52
    oup
    -0.52
    POSITIVE LOGITS
    Else
    1.15
    ifice
    1.10
    nam
    1.03
    chid
    1.02
    acle
    1.00
    acles
    1.00
    chard
    0.98
    lando
    0.95
    ific
    0.94
    acular
    0.89
    Act Density 0.124%

    No Known Activations