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

    Neuronpedia

    INDEX
    Explanations

    words related to gaining fame, popularity, support, or traction

    oai_token-act-pair · gpt-3.5-turbo

    terms related to gaining recognition or popularity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    olute
    -0.62
     halves
    -0.60
     testament
    -0.60
    ynchron
    -0.59
     lookout
    -0.58
    rouse
    -0.58
     arr
    -0.58
    hew
    -0.57
    osite
    -0.57
     suicidal
    -0.55
    POSITIVE LOGITS
     Tradable
    0.75
    ocobo
    0.72
    >]
    0.70
    bach
    0.70
    20439
    0.69
    DEM
    0.68
     Attribution
    0.66
    obyl
    0.65
     IST
    0.64
     veter
    0.63
    Act Density 0.191%

    No Known Activations