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

    Neuronpedia

    INDEX
    Explanations

    references to praise or positive acknowledgment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    transQ
    -0.70
    GEBURTSDATUM
    -0.67
    Geplaatst
    -0.62
    kyl
    -0.60
    Portail
    -0.57
     Answer
    -0.56
    .*")]
    -0.56
    Frust
    -0.54
     desaf
    -0.54
    Grim
    -0.53
    POSITIVE LOGITS
     praise
    2.09
     praising
    1.94
     praises
    1.93
     praised
    1.77
     admiration
    1.65
     Praise
    1.62
     compliments
    1.60
    praise
    1.59
     compliment
    1.59
     admiring
    1.47
    Act Density 0.224%

    No Known Activations