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

    Neuronpedia

    INDEX
    Explanations

    words related to counting or quantifying

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "counters" and related variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     belonging
    -0.67
    yll
    -0.65
    OME
    -0.63
     Log
    -0.62
     ceremonial
    -0.62
     Bohem
    -0.62
     funeral
    -0.62
     ascending
    -0.61
     sacred
    -0.61
    FW
    -0.61
    POSITIVE LOGITS
     countered
    2.86
     counters
    2.74
    ounters
    2.26
     countering
    1.76
     Coun
    1.64
    ounter
    1.42
     counter
    1.32
     rebutt
    1.22
     interrupts
    1.13
    Counter
    1.13
    Act Density 0.027%

    No Known Activations