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

    Neuronpedia

    INDEX
    Explanations

    phrases related to establishing and influencing the direction or mood

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to setting standards or precedents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    leness
    -0.70
    ividual
    -0.69
    ¬¼
    -0.67
     outweigh
    -0.67
    vernment
    -0.62
    ugg
    -0.60
     outwe
    -0.59
     derive
    -0.58
    jug
    -0.58
    enza
    -0.58
    POSITIVE LOGITS
     precedent
    1.17
    tle
    1.05
     tone
    1.02
     sights
    1.00
    flame
    0.97
     precedence
    0.97
     preced
    0.97
     abl
    0.92
     groundwork
    0.90
     pace
    0.86
    Act Density 0.062%

    No Known Activations