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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "withdraw" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    397
    -0.15
    _resolve
    -0.15
    uzzi
    -0.15
    gpu
    -0.14
    884
    -0.14
    EventManager
    -0.14
    gem
    -0.14
    úp
    -0.14
    oa
    -0.13
    639
    -0.13
    POSITIVE LOGITS
     withdrawn
    0.20
     withdrawal
    0.20
     Withdraw
    0.20
     retract
    0.18
     withdrew
    0.18
     withdraw
    0.18
     withdrawing
    0.18
    Withdraw
    0.17
    withdraw
    0.17
     Pull
    0.17
    Act Density 0.071%

    No Known Activations