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

    Neuronpedia

    INDEX
    Explanations

    numbers and percentages

    oai_token-act-pair · gpt-3.5-turbo

    percentage values and opinions related to public and scientific consensus

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Shelter
    -0.64
     Titanic
    -0.63
    ãģĻ
    -0.63
     Pillar
    -0.61
     instead
    -0.61
     Issue
    -0.60
     ASAP
    -0.59
     Navigation
    -0.59
     centerpiece
    -0.58
     Shutterstock
    -0.58
    POSITIVE LOGITS
     alike
    1.01
    dozen
    0.94
    including
    0.94
    heastern
    0.89
    pired
    0.87
    tarians
    0.86
    thodox
    0.83
    idents
    0.83
    pires
    0.83
     polled
    0.82
    Act Density 0.685%

    No Known Activations