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

    Neuronpedia

    INDEX
    Explanations

    instances of the Spanish word "por" and its variations, indicating frequent references to causation or justification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     faſt
    -1.10
     itſelf
    -1.08
     raiſ
    -0.98
     iſt
    -0.98
     greateſt
    -0.97
     myſelf
    -0.96
     ſhe
    -0.95
    paravant
    -0.94
     pleaſure
    -0.92
     Eſ
    -0.91
    POSITIVE LOGITS
     por
    1.98
    por
    1.82
    Por
    1.78
     Por
    1.78
     POR
    1.62
    POR
    1.50
    opor
    1.21
     poros
    0.99
     pelos
    0.98
    pora
    0.94
    Act Density 0.035%

    No Known Activations