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

    Neuronpedia

    INDEX
    Explanations

    words related to actions or accomplishments

    oai_token-act-pair · gpt-3.5-turbo

    terms related to actions or significant events, particularly involving moral or heroic context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    angular
    -0.69
     nervous
    -0.67
    pick
    -0.65
    aspberry
    -0.65
    prim
    -0.65
    Neil
    -0.64
    uzz
    -0.63
     Saunders
    -0.61
     turbulence
    -0.61
     jugg
    -0.61
    POSITIVE LOGITS
     deeds
    3.91
     deed
    3.73
     wills
    1.37
     decree
    1.05
    laws
    0.98
     likeness
    0.97
     bearer
    0.92
     feats
    0.92
    eeds
    0.90
     redeem
    0.89
    Act Density 0.034%

    No Known Activations