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

    Neuronpedia

    INDEX
    Explanations

    words related to moving upwards or gaining power and influence

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the concept of ascension or rising in status

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bytes
    -0.77
     Gore
    -0.73
    chy
    -0.71
     IMAGES
    -0.67
    ãĥIJ
    -0.66
     Geneva
    -0.65
     Grab
    -0.65
     Lieberman
    -0.64
     Goo
    -0.63
     Baird
    -0.63
    POSITIVE LOGITS
     ascended
    1.05
     ascend
    1.04
    endant
    1.04
     ascent
    1.03
    ension
    0.97
    adena
    0.95
    ribed
    0.93
    ancy
    0.89
     asc
    0.88
     ascending
    0.87
    Act Density 0.015%

    No Known Activations