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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of approval in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     
    -0.78
     H
    -0.66
     ge
    -0.63
    ya
    -0.61
     S
    -0.60
    H
    -0.60
     tra
    -0.60
     e
    -0.59
     K
    -0.57
     L
    -0.57
    POSITIVE LOGITS
     approvals
    1.38
     Approval
    1.33
     approval
    1.30
     approves
    1.29
     approve
    1.27
     approving
    1.26
     myſelf
    1.25
     themſelves
    1.18
    approval
    1.18
     disapproval
    1.16
    Act Density 0.067%

    No Known Activations