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

    Neuronpedia

    INDEX
    Explanations

    indications of performance quality and recommendations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     interesante
    -0.62
    Interesting
    -0.61
    interesting
    -0.61
     jspb
    -0.60
     interessantes
    -0.57
     interestingly
    -0.57
     intéressant
    -0.57
     interesting
    -0.54
     Interesting
    -0.54
     schönes
    -0.54
    POSITIVE LOGITS
     outstanding
    1.20
     excellent
    1.03
     top
    1.01
     exceptional
    0.98
     Outstanding
    0.97
     superb
    0.96
     stellar
    0.93
    outstanding
    0.93
    Outstanding
    0.88
     Excellent
    0.85
    Act Density 0.207%

    No Known Activations