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

    Neuronpedia

    INDEX
    Explanations

    instances of numerical values or identifiers in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AndroidJUnit
    -0.57
    marginal
    -0.54
    eze
    -0.54
    Chham
    -0.54
    threaded
    -0.53
    esprit
    -0.53
     broadly
    -0.51
     rêver
    -0.51
    ULT
    -0.50
    liferay
    -0.50
    POSITIVE LOGITS
     {?>
    0.66
    {{$
    0.62
    XmlEnum
    0.60
    (",");
    0.59
    '){
    0.57
    ="{{$
    0.57
    '])){
    0.56
     ricer
    0.56
    {
    0.55
    >",
    0.55
    Act Density 0.095%

    No Known Activations