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

    Neuronpedia

    INDEX
    Explanations

    sentences expressing personal understanding or agreement

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

    "I understand", "makes sense", or similar phrasing

    np_acts-logits-general · gemini-2.0-flash

    expressing understanding or agreement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     CreateTagHelper
    -0.90
     Monfieur
    -0.88
     Majefty
    -0.88
     myſelf
    -0.86
     itſelf
    -0.85
     Jefus
    -0.84
     Efq
    -0.83
     poffe
    -0.82
     useStyles
    -0.81
     pleaſure
    -0.79
    POSITIVE LOGITS
     understandable
    1.86
     understand
    1.77
    understand
    1.76
     Understand
    1.66
    Understand
    1.63
     understands
    1.52
     understanding
    1.43
     understood
    1.40
     Understanding
    1.33
     compren
    1.27
    Act Density 0.204%

    No Known Activations