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

    Neuronpedia

    INDEX
    Explanations

    references to national scale or importance

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the term "national."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    xual
    -0.95
    omething
    -0.95
    eva
    -0.78
    enhagen
    -0.76
    herty
    -0.75
    MODE
    -0.73
    Ware
    -0.72
    tto
    -0.72
    YE
    -0.70
    holes
    -0.68
    POSITIVE LOGITS
    ized
    0.93
    wide
    0.90
     anthem
    0.88
     Geographic
    0.87
    ities
    0.84
    ised
    0.84
    izations
    0.82
    ITY
    0.82
    istic
    0.79
    ization
    0.79
    Act Density 0.036%

    No Known Activations