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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "to" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zw
    -0.17
    aring
    -0.17
    ayah
    -0.17
    RICT
    -0.15
     thuis
    -0.15
    inerary
    -0.15
    _Begin
    -0.14
    baugh
    -0.14
    chaft
    -0.14
    urf
    -0.14
    POSITIVE LOGITS
     bed
    0.37
     extremes
    0.34
     sleep
    0.28
     bat
    0.27
     work
    0.26
     pieces
    0.24
     lengths
    0.24
     war
    0.24
     visit
    0.23
     court
    0.23
    Act Density 0.061%

    No Known Activations