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

    Neuronpedia

    INDEX
    Explanations

    references to discarded or rejected materials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     estekak
    -0.48
    BeginContext
    -0.47
    awtextra
    -0.46
    localctx
    -0.43
     kasarigan
    -0.42
     kaarangay
    -0.42
    readyState
    -0.40
    EndInit
    -0.39
     chev
    -0.39
     CreateTagHelper
    -0.36
    POSITIVE LOGITS
     unused
    0.68
    Unused
    0.67
     discarded
    0.64
     surplus
    0.63
    unused
    0.62
     Unused
    0.62
     leftover
    0.59
     abandoned
    0.56
    ⓧ
    0.56
     Surplus
    0.54
    Act Density 0.410%

    No Known Activations