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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating conditional or hypothetical situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     wynosi
    -0.60
    Dough
    -0.57
     PMID
    -0.55
    っそ
    -0.54
    vaders
    -0.53
    ]\\
    -0.53
    userModel
    -0.53
     ?>
    -0.53
     auber
    -0.53
     }{\
    -0.53
    POSITIVE LOGITS
    følgelig
    1.15
     course
    1.07
    course
    1.00
     COURSE
    0.97
     supuesto
    0.91
    Course
    0.89
     Natürlich
    0.88
     Course
    0.88
    verständlich
    0.87
    ürlich
    0.85
    Act Density 0.064%

    No Known Activations