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

    Neuronpedia

    INDEX
    Explanations

    phrases that involve the word "do" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    å®ĥ
    -0.17
    maid
    -0.16
    rome
    -0.16
    FFFFFFFF
    -0.16
    nel
    -0.15
     migrationBuilder
    -0.15
    lyn
    -0.15
    nid
    -0.15
    stown
    -0.15
    wick
    -0.15
    POSITIVE LOGITS
     we
    0.28
     they
    0.26
    est
    0.25
     you
    0.24
    zens
    0.23
    (es
    0.23
     I
    0.22
    ctest
    0.21
    ctr
    0.21
    oms
    0.20
    Act Density 0.033%

    No Known Activations