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

    Neuronpedia

    INDEX
    Explanations

    words and phrases relating to approvals and authorizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     
    -0.63
     k
    -0.63
    ing
    -0.62
     e
    -0.58
    ae
    -0.58
     K
    -0.55
     kaz
    -0.55
     I
    -0.55
     tra
    -0.55
     ph
    -0.54
    POSITIVE LOGITS
     approval
    2.25
     approved
    2.22
     Approval
    2.22
     approve
    2.17
     approvals
    2.15
     approves
    2.09
     approving
    2.04
     APPROVED
    2.03
     APPROVAL
    2.03
     Approved
    2.03
    Act Density 0.092%

    No Known Activations