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

    Neuronpedia

    INDEX
    Explanations

    forms of the word "articulate."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     fares
    -0.17
    kus
    -0.15
    erk
    -0.15
    à¹ĥหà¸į
    -0.15
    fold
    -0.15
    nier
    -0.15
    furt
    -0.14
    erland
    -0.14
     artwork
    -0.14
    esc
    -0.14
    POSITIVE LOGITS
    facts
    0.25
    ificial
    0.23
    ulate
    0.20
    fact
    0.20
    ifacts
    0.20
    isans
    0.19
    ulation
    0.18
    isan
    0.17
    raft
    0.17
    lse
    0.17
    Act Density 0.006%

    No Known Activations