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

    Neuronpedia

    INDEX
    Explanations

    statements expressing opinions or thoughts related to experiences and observations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     avoient
    -0.66
     élevées
    -0.57
     automatiques
    -0.57
     étoient
    -0.56
     définiti
    -0.56
     montón
    -0.54
     vetro
    -0.54
     chimiques
    -0.53
     élevés
    -0.53
     sociala
    -0.52
    POSITIVE LOGITS
    BeginInit
    0.64
    transQ
    0.63
    ImageContext
    0.57
    CreateModel
    0.56
    MessageState
    0.56
    ]?.
    0.56
    PyErr
    0.53
     further
    0.52
    })`
    0.51
    ytä
    0.51
    Act Density 0.093%

    No Known Activations