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

    Neuronpedia

    INDEX
    Explanations

    elements related to programming and data structures in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     account
    -0.94
     app
    -0.89
     act
    -0.89
     angle
    -0.89
     arc
    -0.88
     attack
    -0.87
     art
    -0.85
     ass
    -0.85
     action
    -0.85
     array
    -0.84
    POSITIVE LOGITS
     normaux
    0.41
     médicaux
    0.41
     particuliers
    0.37
     commerciaux
    0.37
     commerciales
    0.37
     filha
    0.35
     variés
    0.35
     dramatique
    0.35
    AnchorStyles
    0.34
     więc
    0.34
    Act Density 0.717%

    No Known Activations