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

    Neuronpedia

    INDEX
    Explanations

    affirmations or expressions of agreement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Bul
    -0.78
    bul
    -0.70
     "..\..\
    -0.67
    mapsto
    -0.66
    </em>
    -0.66
    Bul
    -0.66
     Koz
    -0.65
    dal
    -0.65
     presence
    -0.64
     Rox
    -0.64
    POSITIVE LOGITS
     Agree
    2.03
     agrees
    1.89
     agree
    1.84
    agree
    1.75
    Agree
    1.70
     Disagree
    1.67
     agreeing
    1.66
     Agreed
    1.65
     Agre
    1.64
     AGRE
    1.64
    Act Density 0.087%

    No Known Activations