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

    Neuronpedia

    INDEX
    Explanations

    various forms of punctuation, particularly periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     
    -0.89
     "
    -0.75
     time
    -0.74
     '
    -0.72
     K
    -0.70
    стори
    -0.69
     مط
    -0.68
     or
    -0.67
     g
    -0.67
     final
    -0.67
    POSITIVE LOGITS
     Monfieur
    1.46
     ainfi
    1.41
     avoient
    1.35
     étoient
    1.33
     plufieurs
    1.26
     Cæsar
    1.22
     myſelf
    1.21
     feroit
    1.20
     uſed
    1.19
     pouvoit
    1.18
    Act Density 0.141%

    No Known Activations