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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "datacenter" with variations in capitalization

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "data" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    shire
    -0.71
    lain
    -0.70
    IDES
    -0.68
    æł
    -0.64
    âķIJ
    -0.64
     proportional
    -0.60
     Papua
    -0.59
    zzi
    -0.59
     prevailed
    -0.59
    ONSORED
    -0.58
    POSITIVE LOGITS
    abases
    1.49
    etime
    1.11
    amation
    1.01
    aclysm
    0.99
    iverse
    0.99
    aminer
    0.99
    abyte
    0.98
    eor
    0.96
    ician
    0.94
    alog
    0.93
    Act Density 0.021%

    No Known Activations