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

    Neuronpedia

    INDEX
    Explanations

    references to user complaints and suggestions in application feedback

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Moreover
    -0.38
     himself
    -0.37
     herself
    -0.36
     Moreover
    -0.32
    あるいは
    -0.31
     bowiem
    -0.31
     moreover
    -0.30
    のである
    -0.30
    himself
    -0.29
    herself
    -0.29
    POSITIVE LOGITS
    Been
    1.20
     Been
    1.20
     Didn
    1.03
     Seems
    1.02
     Gonna
    1.02
     Wasn
    0.98
     Feels
    0.98
     got
    0.98
     gotta
    0.97
    Gonna
    0.97
    Act Density 0.549%

    No Known Activations