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

    Neuronpedia

    INDEX
    Explanations

    specific names of authors and contributors in academic or scientific contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gency
    -0.58
     createSlice
    -0.56
    OrNil
    -0.53
     EClass
    -0.47
    esez
    -0.45
    aneers
    -0.45
    gms
    -0.43
    daille
    -0.43
    roglo
    -0.41
    ybė
    -0.41
    POSITIVE LOGITS
     Zhang
    1.16
     Wang
    1.15
     Zhou
    1.09
     Liu
    1.08
     Zhao
    1.05
     Li
    1.04
     Chen
    1.03
    Wang
    0.99
     Huang
    0.97
    Zhang
    0.96
    Act Density 0.273%

    No Known Activations