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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions involving variables and dimensions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     act
    -0.17
    ected
    -0.16
     Kane
    -0.15
     Dund
    -0.14
     board
    -0.14
    avir
    -0.14
    932
    -0.14
    uh
    -0.14
    /umd
    -0.14
    inja
    -0.13
    POSITIVE LOGITS
    .bt
    0.15
    LT
    0.15
    alist
    0.14
    indr
    0.14
    rips
    0.14
     Standing
    0.14
    aucoup
    0.14
    å±¥
    0.13
    лÑıн
    0.13
    brook
    0.13
    Act Density 0.307%

    No Known Activations