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

    Neuronpedia

    INDEX
    Explanations

    words related to comparisons and relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    isos
    -0.17
    rams
    -0.16
     Hutch
    -0.16
    opus
    -0.15
    eneg
    -0.15
    acre
    -0.15
    hurst
    -0.14
    adolu
    -0.14
    AuthProvider
    -0.14
    avanaugh
    -0.14
    POSITIVE LOGITS
    á»Ŀ
    0.17
     Gill
    0.16
    ož
    0.14
    άνÏĦα
    0.14
    λί
    0.14
    ÏĦικα
    0.14
     edible
    0.14
    udu
    0.13
    .samples
    0.13
    anje
    0.13
    Act Density 0.001%

    No Known Activations