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

    Neuronpedia

    INDEX
    Explanations

    affirmative expressions indicating certainty or affirmation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Maren
    -0.84
     Efq
    -0.74
     OSI
    -0.73
     fVar
    -0.73
     Jefus
    -0.69
     FOS
    -0.68
    ^(@)
    -0.67
    Eri
    -0.67
     Davy
    -0.67
     MOP
    -0.67
    POSITIVE LOGITS
     indeed
    2.11
    indeed
    2.00
    Indeed
    1.95
     Indeed
    1.94
    的确
    1.17
     inderdaad
    1.06
    确实
    1.01
    的確
    0.96
    確實
    0.91
     memang
    0.89
    Act Density 0.052%

    No Known Activations