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

    Neuronpedia

    INDEX
    Explanations

    words related to climbing or ascending

    oai_token-act-pair · gpt-3.5-turbo

    phrases and words associated with upward progression or advancements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anchester
    -0.81
    SourceFile
    -0.69
    ulk
    -0.67
    uncture
    -0.65
    gans
    -0.64
    ouf
    -0.64
    pty
    -0.63
    flix
    -0.63
    anty
    -0.62
    çīĪ
    -0.61
    POSITIVE LOGITS
     ladder
    1.17
     rankings
    1.09
     ranks
    1.06
     stakes
    1.03
     stairs
    1.02
     tiers
    1.00
     altitude
    0.97
     ranking
    0.97
     hierarchy
    0.93
     standings
    0.91
    Act Density 0.347%

    No Known Activations