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

    Neuronpedia

    INDEX
    Explanations

    words related to approval or permission

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "approve" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ngth
    -0.87
    tone
    -0.78
    hole
    -0.78
    lla
    -0.76
    hed
    -0.74
    grave
    -0.69
    istics
    -0.68
    mers
    -0.66
    tal
    -0.65
    monds
    -0.65
    POSITIVE LOGITS
     approvals
    1.00
     unanimously
    0.99
     authorizing
    0.98
     approval
    0.95
     approve
    0.94
     approving
    0.93
     approves
    0.91
     waivers
    0.80
     approved
    0.78
     ratings
    0.75
    Act Density 0.037%

    No Known Activations