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

    Neuronpedia

    INDEX
    Explanations

    references to books and literary works

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    BagConstraints
    -0.41
    orianCalendar
    -0.40
    ScopeManager
    -0.37
     MenuView
    -0.35
    Referanser
    -0.35
     gering
    -0.34
     hábitos
    -0.34
     lastName
    -0.33
     weißt
    -0.32
     relatif
    -0.31
    POSITIVE LOGITS
     fantastic
    0.72
     incredible
    0.68
     superbly
    0.65
     amazing
    0.64
     truly
    0.62
    :✨
    0.60
     wonderful
    0.60
     excellently
    0.60
     superb
    0.60
     brilliantly
    0.60
    Act Density 0.281%

    No Known Activations