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

    Neuronpedia

    INDEX
    Explanations

    numerical quantities followed by units of measure

    oai_token-act-pair · gpt-3.5-turbo

    adverbs indicating frequency or prevalence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atur
    -0.83
    itiveness
    -0.80
    itivity
    -0.76
    enary
    -0.71
    own
    -0.69
    eeds
    -0.69
    emonium
    -0.69
    EEE
    -0.68
    orial
    -0.68
    ravity
    -0.67
    POSITIVE LOGITS
     preferring
    0.87
    entimes
    0.83
     excluding
    0.79
    ãĥĥãĥī
    0.78
    christ
    0.77
     preferably
    0.76
    çĶ°
    0.74
     comprising
    0.73
     unsurprisingly
    0.73
     incidentally
    0.72
    Act Density 0.173%

    No Known Activations