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

    Neuronpedia

    INDEX
    Explanations

    the presence of introductory phrases or statements that indicate a new section or topic transition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     @"/
    -0.60
    待
    -0.55
    JsonHelper
    -0.54
    KHR
    -0.54
    dze
    -0.53
    vise
    -0.52
     Derek
    -0.52
    minecraftforge
    -0.51
    Atsauces
    -0.50
    addCriterion
    -0.50
    POSITIVE LOGITS
     EEU
    0.53
    huri
    0.52
     Trix
    0.51
     Kazan
    0.51
     REA
    0.51
     Aurang
    0.51
     NAN
    0.51
     bandung
    0.51
     madison
    0.50
    <![
    0.50
    Act Density 0.022%

    No Known Activations