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

    Neuronpedia

    INDEX
    Explanations

    words or terms starting with 'id'

    oai_token-act-pair · gpt-3.5-turbo

    instances of the term "idiot" or related variants

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Remastered
    -0.78
    toe
    -0.72
    OUP
    -0.71
     Market
    -0.69
     Afric
    -0.67
    ¬¼
    -0.67
     Goods
    -0.66
     Papua
    -0.65
    OURCE
    -0.64
     Ministers
    -0.64
    POSITIVE LOGITS
    iom
    1.32
    aho
    1.28
    leness
    1.18
    ividual
    1.16
    yll
    1.13
    iop
    1.10
    iotic
    1.09
    iots
    1.05
    uary
    1.00
    iosyn
    0.95
    Act Density 0.011%

    No Known Activations