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

    Neuronpedia

    INDEX
    Explanations

    references to heroic actions or heroic individuals

    oai_token-act-pair · gpt-3.5-turbo

    words associated with heroism and bravery

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enfranch
    -0.83
    upon
    -0.79
    washer
    -0.74
    spring
    -0.72
    estate
    -0.72
    agree
    -0.71
    payer
    -0.71
    essee
    -0.70
    arate
    -0.70
    oval
    -0.68
    POSITIVE LOGITS
     bravery
    1.01
     heroic
    0.93
     daring
    0.92
     heroism
    0.92
     courage
    0.90
     brave
    0.84
     courageous
    0.84
     feats
    0.83
     Expedition
    0.78
     inspiring
    0.75
    Act Density 0.026%

    No Known Activations