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

    Neuronpedia

    INDEX
    Explanations

    phrases related to calculations and evaluations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Goodman
    -0.65
     Vorbe
    -0.60
    tujuan
    -0.58
     bromine
    -0.58
     truce
    -0.56
     BoxDecoration
    -0.55
    колеп
    -0.55
    Gemeinden
    -0.54
     blocco
    -0.52
     nhau
    -0.52
    POSITIVE LOGITS
     calculations
    1.20
     calculation
    1.18
     calculating
    1.18
     Calcul
    1.12
    Calcul
    1.11
     calcul
    1.10
    calcul
    1.10
     Calculate
    1.09
     calcu
    1.09
     calculates
    1.08
    Act Density 0.184%

    No Known Activations