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

    Neuronpedia

    INDEX
    Explanations

    numerical or technical specifications related to devices and components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Jefus
    -1.00
     myſelf
    -0.99
     Theſe
    -0.99
     Efq
    -0.94
     ſeveral
    -0.93
     itſelf
    -0.91
     leaſt
    -0.90
     Diſ
    -0.89
    ſelf
    -0.88
     ſtate
    -0.86
    POSITIVE LOGITS
    ,
    0.68
     Z
    0.51
    /
    0.49
    twimg
    0.48
     e
    0.47
     dirig
    0.46
     his
    0.46
    ;
    0.45
     /
    0.44
     Fig
    0.43
    Act Density 0.254%

    No Known Activations