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

    Neuronpedia

    INDEX
    Explanations

    phrases related to approval processes or legal matters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     canh
    -0.13
    obbies
    -0.13
     à¸ķำ
    -0.12
    ени
    -0.12
    eyse
    -0.12
    \helpers
    -0.11
    æIJį
    -0.11
    aged
    -0.11
    AGED
    -0.11
    iability
    -0.11
    POSITIVE LOGITS
     approval
    0.62
     approvals
    0.53
     approve
    0.52
     Approval
    0.50
     approving
    0.48
    approval
    0.48
     approves
    0.45
     approved
    0.43
    Approval
    0.43
    approve
    0.40
    Act Density 0.679%

    No Known Activations