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

    Neuronpedia

    INDEX
    Explanations

    possessive forms ('s) indicating ownership

    oai_token-act-pair · gpt-3.5-turbo

    possessive forms indicating ownership or affiliation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    livion
    -0.88
     Norn
    -0.86
    èª
    -0.74
    tta
    -0.72
    CVE
    -0.68
     Stella
    -0.68
    otto
    -0.67
    ARDIS
    -0.66
     Schwar
    -0.66
     Hague
    -0.66
    POSITIVE LOGITS
     finest
    0.99
     greatest
    0.92
     contemporaries
    0.90
     inventions
    0.88
     own
    0.86
     earliest
    0.82
     heaviest
    0.81
     busiest
    0.81
     favourite
    0.79
     quir
    0.78
    Act Density 0.076%

    No Known Activations