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

    Neuronpedia

    INDEX
    Explanations

    words related to inflammatory language or situations

    oai_token-act-pair · gpt-3.5-turbo

    terms related to inflammation and inflation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    */(
    -0.89
    DragonMagazine
    -0.78
     Colleges
    -0.74
     Watching
    -0.74
     Teach
    -0.71
    stood
    -0.71
     Lunch
    -0.70
    ³³³³³³³³³³³³³³³³
    -0.70
     Standing
    -0.70
     Massacre
    -0.70
    POSITIVE LOGITS
     infl
    1.13
    orescence
    1.08
    othal
    0.91
    ubric
    0.87
    ations
    0.85
    ights
    0.82
    oster
    0.80
    oresc
    0.79
    atable
    0.76
    atory
    0.76
    Act Density 0.008%

    No Known Activations