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

    Neuronpedia

    INDEX
    Explanations

    superlatives and high-impact terms related to events or entities

    oai_token-act-pair · gpt-3.5-turbo

    superlative adjectives indicating size, severity, or impact

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    akia
    -0.72
    roman
    -0.68
    agra
    -0.68
     Mania
    -0.66
    ÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤ
    -0.64
     Motors
    -0.63
    yi
    -0.63
    psey
    -0.63
    scrib
    -0.63
    ernels
    -0.62
    POSITIVE LOGITS
     imaginable
    0.93
     bidder
    0.81
     stages
    0.75
     possible
    0.75
    hest
    0.72
     conceivable
    0.70
    liest
    0.68
     practicable
    0.67
    seller
    0.66
     unimaginable
    0.65
    Act Density 0.167%

    No Known Activations