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

    Neuronpedia

    INDEX
    Explanations

    the word "Dig" with varying strengths of activation

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns and brand names associated with media or technology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Peninsula
    -0.75
    Reloaded
    -0.73
    VALUE
    -0.71
     VIDE
    -0.68
    >>>>>>>>
    -0.67
     Mara
    -0.67
     Sweden
    -0.66
     Saudis
    -0.66
     CLA
    -0.65
     Saudi
    -0.64
    POSITIVE LOGITS
    Dig
    1.25
    imon
    1.15
    dig
    1.12
    iple
    1.09
    itized
    1.08
     Dig
    1.05
    gers
    0.97
    ible
    0.95
    ging
    0.94
    gment
    0.92
    Act Density 0.003%

    No Known Activations