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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal matters or statements about responsibility

    oai_token-act-pair · gpt-3.5-turbo

    elements of tension or conflict in narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Conclusion
    -0.89
     Additionally
    -0.83
    Additionally
    -0.82
     Lastly
    -0.81
     Secondly
    -0.80
    ãĢį
    -0.77
     Whilst
    -0.74
    razil
    -0.74
     ðŁĺ
    -0.74
    Therefore
    -0.74
    POSITIVE LOGITS
     solitude
    0.90
     scarcely
    0.81
     roar
    0.79
     strangers
    0.79
     melancholy
    0.78
     pilgrimage
    0.78
     shorthand
    0.77
     twent
    0.76
     sprawling
    0.76
     perched
    0.76
    Act Density 1.423%

    No Known Activations