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

    Neuronpedia

    INDEX
    Explanations

    intensifying adverbs that express strong emotions or certainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     is
    -0.22
     itself
    -0.20
     himself
    -0.18
    urus
    -0.18
    ’s
    -0.17
     themselves
    -0.17
    entiful
    -0.16
     isn
    -0.16
     reck
    -0.15
     herself
    -0.15
    POSITIVE LOGITS
    've
    0.22
     have
    0.20
     don
    0.20
    ’ve
    0.19
     دارÙħ
    0.18
     haven
    0.18
     estamos
    0.17
    'm
    0.16
    iyim
    0.16
     jsem
    0.16
    Act Density 0.085%

    No Known Activations