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

    Neuronpedia

    INDEX
    Explanations

    negative or adverse sentiment in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ulhu
    -0.76
     layoffs
    -0.75
     Savings
    -0.71
     Parenthood
    -0.70
     skeptics
    -0.68
     Tycoon
    -0.65
     Dickinson
    -0.65
     savings
    -0.64
     assurances
    -0.64
     Apocalypse
    -0.64
    POSITIVE LOGITS
    facing
    1.35
    most
    1.13
    handed
    1.11
    hand
    1.08
    west
    1.08
    dimensional
    1.08
    direction
    1.05
    side
    1.05
    east
    1.04
    mounted
    1.03
    Act Density 0.015%

    No Known Activations