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

    Neuronpedia

    INDEX
    Explanations

    references to future strategies and intentions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     patties
    -0.37
    Secondary
    -0.37
    好看
    -0.36
     foncé
    -0.36
    secondary
    -0.35
    InOrder
    -0.35
     hero
    -0.35
     boneca
    -0.34
     ringer
    -0.34
    aged
    -0.34
    POSITIVE LOGITS
     plans
    0.88
     recommendations
    0.85
    Plans
    0.81
     Plans
    0.81
    Recommendations
    0.74
     suggestions
    0.73
    recommendations
    0.73
     proposals
    0.73
     Recommendations
    0.73
     advice
    0.71
    Act Density 0.168%

    No Known Activations