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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing opinions and thoughts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    adoc
    -0.54
     cherchez
    -0.54
     מלא
    -0.50
     emplois
    -0.49
    렵
    -0.49
     ordres
    -0.49
     codes
    -0.49
    Publishers
    -0.47
     calendriers
    -0.47
     pulito
    -0.47
    POSITIVE LOGITS
     opinions
    0.97
     Opinions
    0.94
    Opinions
    0.90
    Thoughts
    0.90
     opinion
    0.87
     Thoughts
    0.87
    opinions
    0.87
     opin
    0.77
    opinion
    0.75
     Opinion
    0.74
    Act Density 0.104%

    No Known Activations