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

    Neuronpedia

    INDEX
    Explanations

    numeric values and their relationships in a technical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Jefus
    -1.04
     Theſe
    -1.03
     Efq
    -1.01
     myſelf
    -1.01
     ſeveral
    -0.98
    ſelves
    -0.93
     leaſt
    -0.93
    ſelf
    -0.93
     Diſ
    -0.92
     Majefty
    -0.91
    POSITIVE LOGITS
    ,
    0.76
    /
    0.57
     /
    0.50
     his
    0.49
     dirig
    0.48
     e
    0.47
     Z
    0.45
    ;
    0.43
     
    0.43
     want
    0.43
    Act Density 0.141%

    No Known Activations