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

    Neuronpedia

    INDEX
    Explanations

    the word "Ham" preceded by various contexts and intensities

    oai_token-act-pair · gpt-3.5-turbo

    references to "Hamlet."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uality
    -0.74
    terday
    -0.74
    CLASSIFIED
    -0.69
    ç«
    -0.69
     Leone
    -0.68
    Downloadha
    -0.65
     Staples
    -0.65
    igslist
    -0.64
    ãģį
    -0.64
    igion
    -0.64
    POSITIVE LOGITS
    mers
    1.26
    elin
    1.17
    pton
    1.14
    strings
    1.14
    ster
    1.10
    ilton
    1.08
    monds
    0.98
    sters
    0.98
    mer
    0.97
    ild
    0.95
    Act Density 0.010%

    No Known Activations