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

    Neuronpedia

    INDEX
    Explanations

    positive and comparative adjectives reflecting quality or state of being

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     better
    -0.23
     Better
    -0.19
     besser
    -0.19
     tá»ijt
    -0.17
    oba
    -0.17
    better
    -0.17
     melhor
    -0.17
     best
    -0.17
     mejor
    -0.17
     meilleure
    -0.16
    POSITIVE LOGITS
    su
    0.23
    -su
    0.22
    Su
    0.20
     Su
    0.20
     served
    0.19
     suited
    0.18
    -position
    0.18
     situated
    0.17
     att
    0.17
     disposed
    0.17
    Act Density 0.049%

    No Known Activations