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

    Neuronpedia

    INDEX
    Explanations

    words that indicate strong emotions or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    èĢħãģ®
    -0.15
    kea
    -0.14
    andex
    -0.14
    بÙĪاسطة
    -0.14
     ES
    -0.14
    ardin
    -0.14
    LER
    -0.13
     Essex
    -0.13
    gles
    -0.13
    uccess
    -0.13
    POSITIVE LOGITS
    ed
    1.71
    edBy
    0.94
    edb
    0.81
    edl
    0.80
    edn
    0.79
    ED
    0.69
    edm
    0.68
    edTextBox
    0.60
    edd
    0.59
    edata
    0.59
    Act Density 0.313%

    No Known Activations