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

    Neuronpedia

    INDEX
    Explanations

    high-frequency, impactful keywords that indicate significant actions or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    akov
    -0.17
    ycastle
    -0.17
    ána
    -0.16
    elian
    -0.16
    orate
    -0.15
    -Za
    -0.15
    uisine
    -0.15
    ycin
    -0.15
     Horton
    -0.15
    onet
    -0.15
    POSITIVE LOGITS
    ante
    0.16
    irsch
    0.15
    spr
    0.15
    antes
    0.14
     anterior
    0.14
     Cru
    0.14
     sortOrder
    0.14
     Dek
    0.13
     intr
    0.13
    ord
    0.13
    Act Density 0.003%

    No Known Activations