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

    Neuronpedia

    INDEX
    Explanations

    numerical quantities related to counts

    oai_token-act-pair · gpt-3.5-turbo

    references to the number 200 and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atto
    -0.67
    anos
    -0.66
    rh
    -0.66
    hew
    -0.62
    rift
    -0.61
    iosyncr
    -0.60
    OHN
    -0.60
    amy
    -0.60
    Reviewer
    -0.60
    Leary
    -0.60
    POSITIVE LOGITS
     200
    3.01
     400
    2.36
     300
    2.30
     500
    2.23
     250
    2.18
     150
    2.14
     600
    2.08
     800
    1.97
     1000
    1.95
     3000
    1.94
    Act Density 0.021%

    No Known Activations