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

    Neuronpedia

    INDEX
    Explanations

    mentions of approvals or agreements

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "approve" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ngth
    -0.74
    tone
    -0.72
    grave
    -0.71
    lla
    -0.70
    ottesville
    -0.68
    toe
    -0.68
    tal
    -0.66
    monds
    -0.66
     Islands
    -0.65
     Hole
    -0.65
    POSITIVE LOGITS
     unanimously
    1.03
     approve
    0.98
     approval
    0.97
     approvals
    0.96
     approving
    0.92
     authorizing
    0.92
     approves
    0.91
    votes
    0.80
     ratings
    0.79
    clinton
    0.74
    Act Density 0.029%

    No Known Activations