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

    Neuronpedia

    INDEX
    Explanations

    repeated phrases or structures, particularly involving the word "to."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    up
    -0.18
    ro
    -0.17
    irc
    -0.16
    wood
    -0.15
     anc
    -0.15
    au
    -0.14
    vol
    -0.14
     pii
    -0.14
    ago
    -0.14
    rb
    -0.14
    POSITIVE LOGITS
    ehr
    0.19
    asters
    0.19
    ools
    0.18
    plevel
    0.17
    othy
    0.17
    pek
    0.16
    aster
    0.16
    lags
    0.16
    ASTER
    0.16
    eh
    0.15
    Act Density 0.166%

    No Known Activations