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

    Neuronpedia

    INDEX
    Explanations

    sections that summarize findings, conclusions, and discussions in text

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     myſelf
    -1.16
     Monfieur
    -1.10
     themſelves
    -1.05
     Jefus
    -1.02
     itſelf
    -1.02
    RenderAtEndOf
    -1.02
     houſe
    -0.99
     pleaſure
    -0.97
     Efq
    -0.97
     Houſe
    -0.96
    POSITIVE LOGITS
    CodeAttribute
    0.42
    ândia
    0.42
    spli
    0.40
     d
    0.38
     di
    0.38
    大正
    0.38
    INDEX
    0.38
     (
    0.37
     fue
    0.36
     c
    0.36
    Act Density 0.016%

    No Known Activations