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

    Neuronpedia

    INDEX
    Explanations

    phrases related to popularity and frequency among certain groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     terminated
    -0.84
     Transcript
    -0.77
    arations
    -0.75
    Letter
    -0.70
     equival
    -0.70
    gency
    -0.70
    claimer
    -0.70
    olon
    -0.67
     transcript
    -0.67
    olicy
    -0.66
    POSITIVE LOGITS
     locals
    1.01
     enthusiasts
    0.97
     tourists
    0.96
     collectors
    0.94
     travelers
    0.92
     conservatives
    0.88
     environmentalists
    0.88
     hunters
    0.85
     beginners
    0.84
     Europeans
    0.84
    Act Density 0.110%

    No Known Activations