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

    Neuronpedia

    INDEX
    Explanations

    repeated phrases and punctuation in text

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

    Follows conversational text or questions

    np_acts-logits-general · gemini-2.0-flash

    punctuation followed by short words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     myſelf
    -1.48
     Jefus
    -1.35
     Monfieur
    -1.35
     himſelf
    -1.33
     Efq
    -1.33
     itſelf
    -1.29
     themſelves
    -1.23
     Shakspeare
    -1.22
     Houſe
    -1.22
     Chriftian
    -1.19
    POSITIVE LOGITS
     we
    0.88
     the
    0.85
     it
    0.84
     z
    0.84
     in
    0.83
     so
    0.82
     un
    0.81
     n
    0.81
     con
    0.81
     and
    0.80
    Act Density 0.494%

    No Known Activations