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

    Neuronpedia

    INDEX
    Explanations

    phrases or words related to numbered lists or bullet points

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "ec" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    MENTS
    -0.63
    FTWARE
    -0.63
     Ashe
    -0.63
     Desire
    -0.62
     Maker
    -0.62
    NOW
    -0.60
     Featured
    -0.60
     Showdown
    -0.59
    Glass
    -0.59
     Ou
    -0.59
    POSITIVE LOGITS
    stasy
    1.27
    uador
    1.18
    utive
    1.15
    lectic
    1.08
    ogl
    1.04
    ounters
    1.01
    oder
    0.99
    urrent
    0.97
    ounter
    0.96
    ourt
    0.96
    Act Density 0.017%

    No Known Activations