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

    Neuronpedia

    INDEX
    Explanations

    the concept of quantity, particularly the term "more" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lance
    -0.83
    abad
    -0.77
    Rus
    -0.75
    vier
    -0.75
    ãĥĥãĥĪ
    -0.72
    staking
    -0.72
    hell
    -0.70
    velt
    -0.70
    Joy
    -0.66
    odor
    -0.66
    POSITIVE LOGITS
     layers
    0.99
     consecutive
    0.95
     instances
    0.94
     hundred
    0.88
     phases
    0.87
     iterations
    0.87
     occasions
    0.86
     branches
    0.86
     columns
    0.86
     copies
    0.86
    Act Density 0.022%

    No Known Activations