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

    Neuronpedia

    INDEX
    Explanations

    references to models and methodologies in scientific research

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĸ
    -0.13
     ãĢľ
    -0.13
    orz
    -0.13
    obs
    -0.13
     perverse
    -0.13
    inf
    -0.13
     determinant
    -0.13
    kü
    -0.13
     Zum
    -0.13
    lle
    -0.13
    POSITIVE LOGITS
     models
    0.57
     model
    0.52
     Models
    0.49
    models
    0.46
    模åŀĭ
    0.46
    Models
    0.44
    model
    0.43
     Model
    0.41
     modèle
    0.40
    -model
    0.40
    Act Density 0.194%

    No Known Activations