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

    Neuronpedia

    INDEX
    Explanations

    references to tribal affiliations and relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     van
    -0.54
     hip
    -0.51
     float
    -0.51
     Hip
    -0.48
     floated
    -0.47
    理工
    -0.47
     καρ
    -0.46
     επι
    -0.46
     ti
    -0.45
     gene
    -0.45
    POSITIVE LOGITS
     becauſe
    1.06
     whoſe
    0.97
     itſelf
    0.95
     raiſ
    0.93
     myſelf
    0.92
     purpoſe
    0.92
     Theſe
    0.91
     pleaſure
    0.91
     Jefus
    0.91
     uſe
    0.90
    Act Density 2.597%

    No Known Activations