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

    Neuronpedia

    INDEX
    Explanations

    numerical values and their significance in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     poch
    -0.65
    dorf
    -0.62
     inne
    -0.59
    TextHelper
    -0.59
     המצ
    -0.58
     Haller
    -0.57
    みてください
    -0.57
     Lott
    -0.55
    يج
    -0.54
    kut
    -0.54
    POSITIVE LOGITS
     kasarigan
    0.84
    0.75
     religieuses
    0.74
    KommentareTeilen
    0.73
    Celeste
    0.72
     vidare
    0.72
     soeur
    0.70
     Administrativna
    0.70
     verksamhet
    0.69
    ohjel
    0.68
    Act Density 0.318%

    No Known Activations