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

    Neuronpedia

    INDEX
    Explanations

    mentions of physical rigidity or resistance

    oai_token-act-pair · gpt-3.5-turbo

    references to stiffness and rigidness in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orate
    -0.78
     Hiroshima
    -0.74
     Partnership
    -0.72
    ulhu
    -0.68
     Purpose
    -0.67
     Occupations
    -0.66
     Camb
    -0.64
     Blessed
    -0.63
     Paradise
    -0.63
     Augusta
    -0.63
    POSITIVE LOGITS
     stiff
    1.09
    eners
    0.95
    nesses
    0.94
     challeng
    0.91
    ening
    0.91
     undermin
    0.91
     nodd
    0.89
    ened
    0.83
     embr
    0.80
     streng
    0.79
    Act Density 0.006%

    No Known Activations