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

    Neuronpedia

    INDEX
    Explanations

    the word "For" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <eos>
    -0.42
     rep
    -0.41
     cho
    -0.38
    TextBoxColumn
    -0.36
     count
    -0.35
    точници
    -0.34
    HasIndex
    -0.32
     ins
    -0.32
    ynb
    -0.31
     (
    -0.31
    POSITIVE LOGITS
     houſe
    0.73
     Monfieur
    0.72
     Houſe
    0.71
     ſeine
    0.70
     Geiſt
    0.70
     myſelf
    0.69
    niſſe
    0.69
    ésultats
    0.69
    ſehen
    0.68
    ﹧
    0.68
    Act Density 0.674%

    No Known Activations