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

    Neuronpedia

    INDEX
    Explanations

    sequences of repeated symbols or formatting elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ..."
    -0.56
    ?”.
    -0.54
    !”.
    -0.52
    ."),
    -0.51
    !”
    -0.51
     typelib
    -0.51
    !",
    -0.50
    AddTagHelper
    -0.50
    ."<
    -0.49
    ?".
    -0.49
    POSITIVE LOGITS
     propOrder
    0.73
    gonic
    0.63
    endphp
    0.56
     betweenstory
    0.53
     percolation
    0.52
    ⠀⠀
    0.51
    telah
    0.51
    /////
    0.49
     FixedUpdate
    0.49
     librement
    0.49
    Act Density 0.597%

    No Known Activations