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

    Neuronpedia

    INDEX
    Explanations

    expressions of gratitude and positive impact on the world

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

    purpose and meaning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     strap
    -0.41
     straps
    -0.40
     dropping
    -0.40
     dipping
    -0.38
     Pla
    -0.38
     Hours
    -0.37
     o
    -0.37
     Kö
    -0.36
     latest
    -0.36
     kek
    -0.36
    POSITIVE LOGITS
    rungsseite
    0.63
     transfieras
    0.51
    FlatAppearance
    0.48
    Ehrungen
    0.48
    Jereo
    0.47
    Życiorys
    0.46
     dignité
    0.46
     themſelves
    0.45
    лтемелер
    0.44
    TagMode
    0.43
    Act Density 0.006%

    No Known Activations