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

    Neuronpedia

    INDEX
    Explanations

    references to programming frameworks and libraries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     "
    -0.60
     
    -0.55
     --
    -0.50
     in
    -0.50
     start
    -0.48
     #
    -0.46
    "
    -0.46
     a
    -0.44
     ''
    -0.44
    #
    -0.44
    POSITIVE LOGITS
     houſe
    1.10
     pleaſure
    0.92
     Houſe
    0.91
     Diſ
    0.90
    RetentionPolicy
    0.89
     ſch
    0.88
     Jefus
    0.88
     ſta
    0.85
     purpoſe
    0.83
     itſelf
    0.83
    Act Density 0.011%

    No Known Activations