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

    Neuronpedia

    INDEX
    Explanations

    sections and labels related to titles and captions in academic or scientific documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     riuscito
    -0.63
     étoient
    -0.61
     scaricare
    -0.60
     costumi
    -0.60
     dipendenti
    -0.59
     mangiare
    -0.59
     scattata
    -0.58
    alnız
    -0.58
     avoient
    -0.57
     organisé
    -0.56
    POSITIVE LOGITS
    Title
    1.53
     Title
    1.27
    title
    1.11
     title
    1.03
     TITLE
    0.97
     autorytatywna
    0.95
     titles
    0.84
    TITLE
    0.84
     Titel
    0.84
     Titles
    0.84
    Act Density 0.022%

    No Known Activations