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

    Neuronpedia

    INDEX
    Explanations

    phrases related to possession or association

    oai_token-act-pair · gpt-3.5-turbo

    references to groups or categories in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    urus
    -0.82
    FontSize
    -0.68
    uart
    -0.66
    cius
    -0.65
    aph
    -0.65
    reporting
    -0.62
     Clouds
    -0.61
    fty
    -0.60
    umbnails
    -0.60
    iries
    -0.60
    POSITIVE LOGITS
     belongs
    0.81
     ours
    0.77
     represents
    0.73
     initiative
    0.71
     endeavor
    0.66
    ATURE
    0.66
    OULD
    0.65
     extends
    0.64
     phenomenon
    0.62
     shenan
    0.61
    Act Density 0.484%

    No Known Activations