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

    Neuronpedia

    INDEX
    Explanations

    elements related to code or configuration settings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tons
    -0.71
     conferences
    -0.70
     helicopters
    -0.69
     bets
    -0.67
     vans
    -0.65
     disperse
    -0.65
     constituencies
    -0.64
     crops
    -0.64
     budgets
    -0.63
     consultants
    -0.62
    POSITIVE LOGITS
    969
    0.82
    Īè
    0.81
    775
    0.69
    382
    0.69
    zz
    0.67
    ľ
    0.67
    luaj
    0.67
    985
    0.67
    facing
    0.66
    âĿ
    0.65
    Act Density 0.083%

    No Known Activations