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

    Neuronpedia

    INDEX
    Explanations

    references to sports events and teams

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     behaviors
    -0.20
     favors
    -0.20
    favor
    -0.18
     favor
    -0.18
    AVOR
    -0.18
     rumor
    -0.18
    iam
    -0.17
     rumored
    -0.17
     rumors
    -0.17
     favorable
    -0.17
    POSITIVE LOGITS
     attacking
    0.19
     Premier
    0.18
     Test
    0.18
     scalp
    0.18
     fixture
    0.16
     spell
    0.16
     personnel
    0.15
     Liga
    0.15
    957
    0.15
     Prem
    0.15
    Act Density 0.126%

    No Known Activations