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

    Neuronpedia

    INDEX
    Explanations

    comparisons in sentences

    oai_token-act-pair · gpt-3.5-turbo

    phrases that involve comparisons or references to groups or individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    istries
    -0.88
    arios
    -0.71
    ONEY
    -0.70
    akeru
    -0.61
    liga
    -0.61
     thanking
    -0.59
    */(
    -0.59
    ERSON
    -0.59
    ategy
    -0.57
    ENSE
    -0.56
    POSITIVE LOGITS
     slightest
    0.78
     usual
    0.77
     predecessors
    0.73
     rivals
    0.70
     ordinary
    0.69
    usual
    0.69
     actual
    0.68
    verages
    0.67
     counterparts
    0.67
     competitors
    0.64
    Act Density 0.214%

    No Known Activations