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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, particularly periods and brackets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     nac
    -0.72
    shmi
    -0.71
    стори
    -0.70
     yhte
    -0.67
     association
    -0.66
     مط
    -0.66
     Tind
    -0.65
    mappedBy
    -0.65
    плек
    -0.64
     
    -0.64
    POSITIVE LOGITS
     Monfieur
    1.14
     ainfi
    1.09
     avoient
    1.06
     étoient
    1.06
     plufieurs
    1.02
    .&
    0.98
     étoit
    0.97
     Cæsar
    0.96
     pouvoit
    0.95
     myſelf
    0.94
    Act Density 0.181%

    No Known Activations