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

    Neuronpedia

    INDEX
    Explanations

    words related to physical elevation or increase

    oai_token-act-pair · gpt-3.5-turbo

    terms related to height, particularly of buildings and structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     buf
    -0.68
     bad
    -0.66
     gamb
    -0.65
     inserted
    -0.63
     trophies
    -0.62
     committed
    -0.60
     coin
    -0.58
     mul
    -0.58
     immobil
    -0.58
     states
    -0.58
    POSITIVE LOGITS
    rise
    4.69
    rises
    2.86
    rising
    1.96
     Rise
    1.45
    shine
    1.37
     rise
    1.29
    raise
    1.28
    ousse
    1.19
    growth
    1.11
    ris
    1.09
    Act Density 0.014%

    No Known Activations