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

    Neuronpedia

    INDEX
    Explanations

    discussions about changes or developments in situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Junk
    -0.18
    uen
    -0.16
    WND
    -0.15
    ec
    -0.15
    elim
    -0.15
    ULK
    -0.15
    -regexp
    -0.14
    aging
    -0.14
    land
    -0.14
    wind
    -0.14
    POSITIVE LOGITS
    -caption
    0.17
    uxe
    0.16
     vX
    0.15
    instein
    0.15
    -sheet
    0.14
    æĿ
    0.14
    anooga
    0.14
    anus
    0.14
    ilibrium
    0.14
    illes
    0.13
    Act Density 0.086%

    No Known Activations