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

    Neuronpedia

    INDEX
    Explanations

    the word "thousand" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Cree
    -0.16
    ayas
    -0.15
    olic
    -0.15
    icon
    -0.15
    room
    -0.14
    ault
    -0.14
    ogle
    -0.14
    uman
    -0.14
    irk
    -0.14
     Torres
    -0.13
    POSITIVE LOGITS
    fold
    0.21
    ieves
    0.18
    zew
    0.17
    -fold
    0.16
    awi
    0.16
    ittest
    0.16
    orman
    0.16
    ITO
    0.16
    th
    0.15
    naire
    0.15
    Act Density 0.078%

    No Known Activations