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

    Neuronpedia

    INDEX
    Explanations

    instances of the verb "do" and its various conjugations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    urette
    -0.17
    egin
    -0.17
    orro
    -0.16
    paring
    -0.15
    paragraph
    -0.15
    rema
    -0.14
    avra
    -0.14
    лÑİб
    -0.14
    urge
    -0.14
    rror
    -0.14
    POSITIVE LOGITS
     unto
    0.28
     battle
    0.24
     right
    0.24
     damage
    0.23
     everything
    0.22
     favors
    0.22
     what
    0.22
     things
    0.22
     whatever
    0.22
    battle
    0.22
    Act Density 0.080%

    No Known Activations