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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "to" indicating various actions or conclusions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Datuak
    -0.92
     للمعارف
    -0.85
     myſelf
    -0.81
     itſelf
    -0.80
    TagMode
    -0.75
     الحره
    -0.75
    oneofs
    -0.74
     Monfieur
    -0.74
    AddHtmlAttribute
    -0.73
    Portale
    -0.70
    POSITIVE LOGITS
    ",
    0.52
     împ
    0.51
     reach
    0.49
    ,
    0.49
    सि
    0.47
    هرة
    0.46
    </h2>
    0.46
    Reaching
    0.46
     kaca
    0.46
     most
    0.46
    Act Density 0.084%

    No Known Activations