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

    Neuronpedia

    INDEX
    Explanations

    percentages and statistical changes in data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    est
    -0.19
    etri
    -0.15
    landers
    -0.15
    ieder
    -0.15
    scape
    -0.14
    kö
    -0.14
    thro
    -0.14
    inger
    -0.14
    Linked
    -0.14
    ANTED
    -0.14
    POSITIVE LOGITS
    acas
    0.15
    .scalablytyped
    0.14
    Æ°á»Ľ
    0.14
    OLTIP
    0.14
    OLA
    0.14
    Overlap
    0.14
    imir
    0.14
    ddy
    0.14
    oul
    0.14
    PLY
    0.13
    Act Density 0.031%

    No Known Activations