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

    Neuronpedia

    INDEX
    Explanations

    references to data models

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     houſe
    -0.94
     Anſ
    -0.90
     Monfieur
    -0.87
     Shakspeare
    -0.86
     Houſe
    -0.86
     Theſe
    -0.84
     Efq
    -0.82
     Shaksp
    -0.81
    UserScript
    -0.81
     Jefus
    -0.80
    POSITIVE LOGITS
    Models
    1.93
     models
    1.90
    Model
    1.86
     Models
    1.84
     Model
    1.84
    models
    1.65
     MODEL
    1.62
     model
    1.61
     MODELS
    1.60
    MODEL
    1.49
    Act Density 0.134%

    No Known Activations