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

    Neuronpedia

    INDEX
    Explanations

    numerical data and measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Samo
    -0.82
     Krä
    -0.72
     Rama
    -0.72
     pira
    -0.71
     aproximada
    -0.70
    rama
    -0.68
    tivism
    -0.68
    ensdag
    -0.67
     SRA
    -0.67
    MENTE
    -0.67
    POSITIVE LOGITS
    0
    1.20
     TEN
    0.94
    TemporalType
    0.89
    ValueGeneration
    0.85
    TEN
    0.84
     Tencent
    0.83
     FontWeight
    0.82
    Ten
    0.82
     Ten
    0.81
    Loh
    0.81
    Act Density 0.439%

    No Known Activations