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

    Neuronpedia

    INDEX
    Explanations

    details related to official or formal matters

    oai_token-act-pair · gpt-3.5-turbo

    references to assessments and evaluations within a legal or formal context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     trendy
    -0.81
     Scandinav
    -0.79
    population
    -0.78
     dystopian
    -0.77
     paradise
    -0.76
     futuristic
    -0.76
     eco
    -0.76
     badass
    -0.76
     addictive
    -0.73
     selfie
    -0.72
    POSITIVE LOGITS
    Asked
    1.16
     testified
    1.11
     contradicted
    1.06
     contended
    1.04
    answered
    1.01
     objected
    0.97
     clarified
    0.95
     disagreed
    0.95
    sequently
    0.94
    Nonetheless
    0.91
    Act Density 1.113%

    No Known Activations