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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "withdraw" at various inflections

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "withdraw" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iola
    -0.72
     Collider
    -0.72
    yright
    -0.67
    odic
    -0.64
    vous
    -0.63
    vironments
    -0.63
    transform
    -0.63
    Catalog
    -0.62
     Parish
    -0.62
    esan
    -0.61
    POSITIVE LOGITS
     withdrawals
    0.87
    avorite
    0.79
     withdrawal
    0.75
    leted
    0.72
    ends
    0.71
     withdraw
    0.71
    ruck
    0.66
    backs
    0.65
    itives
    0.65
    uary
    0.64
    Act Density 0.021%

    No Known Activations