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

    Neuronpedia

    INDEX
    Explanations

    second person pronouns

    oai_token-act-pair · gpt-3.5-turbo

    personal pronouns indicating involvement or participation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    advertisement
    -0.79
     Others
    -0.69
    00200000
    -0.64
    Entry
    -0.62
    argon
    -0.61
     Replacement
    -0.60
    prime
    -0.59
     Apart
    -0.59
    indal
    -0.59
    arine
    -0.58
    POSITIVE LOGITS
     traveled
    0.88
     visited
    0.85
     embarked
    0.84
    've
    0.83
     celebrated
    0.82
     encount
    0.81
     ventured
    0.79
     travelled
    0.78
     toured
    0.78
     learned
    0.78
    Act Density 0.232%

    No Known Activations