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

    Neuronpedia

    INDEX
    Explanations

    the word 'dozen'

    oai_token-act-pair · gpt-3.5-turbo

    terms related to counting or quantifying groups of items or people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ¼ãĥ«
    -0.82
    ITS
    -0.70
    lights
    -0.69
    its
    -0.66
    pants
    -0.65
    bas
    -0.65
    lance
    -0.63
    poses
    -0.62
    eatures
    -0.61
    powers
    -0.61
    POSITIVE LOGITS
     different
    1.06
     dozen
    1.05
     distinct
    1.00
     apiece
    0.97
     consecutive
    0.96
     separate
    0.96
     successive
    0.88
    dozen
    0.87
     simultaneous
    0.87
     thousand
    0.82
    Act Density 0.216%

    No Known Activations