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

    Neuronpedia

    INDEX
    Explanations

    first-person pronoun usage

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

    "I" followed by verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Hostname
    -0.43
     sauce
    -0.37
     provider
    -0.34
     your
    -0.34
     oms
    -0.33
     prin
    -0.32
     teenage
    -0.32
     moto
    -0.32
     mo
    -0.32
     rule
    -0.31
    POSITIVE LOGITS
    +#+#
    0.68
    DockStyle
    0.66
     NSCoder
    0.59
    OGND
    0.57
    Datuak
    0.57
    Diwedd
    0.52
     gyhoeddwyd
    0.49
    ArgumentParser
    0.47
    AFX
    0.47
    Попис
    0.47
    Act Density 0.019%

    No Known Activations