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

    Neuronpedia

    INDEX
    Explanations

    emphatic modifiers that intensify attributes or qualities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     spé
    -0.48
    MockBean
    -0.47
    примеча
    -0.45
     الرياضيه
    -0.45
    FailureListener
    -0.44
     huom
    -0.43
     queſta
    -0.43
     nombreux
    -0.43
     plufieurs
    -0.43
    lebo
    -0.43
    POSITIVE LOGITS
     completely
    1.56
     Completely
    1.54
    Completely
    1.47
     totally
    1.45
     entirely
    1.30
    completely
    1.29
    totally
    1.27
     completamente
    1.27
     Totally
    1.23
    Totally
    1.20
    Act Density 0.230%

    No Known Activations