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

    Neuronpedia

    INDEX
    Explanations

    references to quality or refinement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ulhu
    -0.82
    raltar
    -0.76
    jri
    -0.75
    osponsors
    -0.74
     Kut
    -0.72
     thwarted
    -0.72
    ataka
    -0.72
    rush
    -0.70
    soDeliveryDate
    -0.70
    urg
    -0.69
    POSITIVE LOGITS
     tuning
    1.02
     tuned
    0.93
     Gael
    0.90
     arts
    0.87
     linen
    0.82
     tune
    0.82
     dining
    0.80
     print
    0.78
     art
    0.76
     vers
    0.72
    Act Density 0.011%

    No Known Activations