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

    Neuronpedia

    INDEX
    Explanations

    the beginning of sentences or paragraphs

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

    Follows "said"

    np_acts-logits-general · gemini-2.0-flash

    speech attribution

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     дан
    -0.69
    :✨
    -0.67
    jestic
    -0.66
     Whilst
    -0.64
     oftentimes
    -0.64
    apunov
    -0.63
     Subsequently
    -0.62
     Due
    -0.61
    ensee
    -0.61
    Whilst
    -0.61
    POSITIVE LOGITS
     daß
    0.53
     mußten
    0.53
     дописавши
    0.52
     useCallback
    0.52
     metálica
    0.51
    tagHelperRunner
    0.51
    subplots
    0.49
     müßte
    0.48
     Cinéma
    0.48
    noscript
    0.47
    Act Density 0.236%

    No Known Activations