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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a need for action or improvement

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a call to action or the necessity for change

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anka
    -0.78
    Runner
    -0.75
    paio
    -0.72
    ullivan
    -0.69
    ozyg
    -0.65
    ãĤ§
    -0.65
    washer
    -0.65
    iannopoulos
    -0.64
    ilty
    -0.63
     Milky
    -0.62
    POSITIVE LOGITS
     urgently
    1.26
     reforms
    1.15
     rethink
    1.13
     reform
    1.13
     reforming
    1.09
     overhaul
    1.06
     improvement
    1.04
     improvements
    1.02
     improving
    0.97
     improved
    0.97
    Act Density 0.707%

    No Known Activations