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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to comparison and compatibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    action completion or statement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    DMETHOD
    -0.41
    modelBuilder
    -0.40
     deleteById
    -0.39
     plufieurs
    -0.39
    ":[{
    -0.38
    bootstrapcdn
    -0.38
     dataTable
    -0.38
     betweenstory
    -0.38
     onCreate
    -0.37
     zwierzę
    -0.37
    POSITIVE LOGITS
    0.52
     autorytatywna
    0.46
     Damn
    0.41
    يكب
    0.41
    AddTagHelper
    0.41
    LookAnd
    0.41
    ************/
    0.40
     WRONG
    0.40
    Damn
    0.40
     damn
    0.39
    Act Density 0.039%

    No Known Activations