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

    Neuronpedia

    INDEX
    Explanations

    forms of the verb "do" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orro
    -0.16
    avra
    -0.15
    wear
    -0.15
    anton
    -0.15
    áš
    -0.15
    otta
    -0.14
    paring
    -0.14
    425
    -0.14
    trace
    -0.14
    365
    -0.14
    POSITIVE LOGITS
     away
    0.26
     Away
    0.21
     battle
    0.21
     everything
    0.20
     justice
    0.20
     violence
    0.19
     ye
    0.18
     damage
    0.18
     unto
    0.18
    le
    0.18
    Act Density 0.064%

    No Known Activations