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

    Neuronpedia

    INDEX
    Explanations

    conversational phrases indicating user control and commands

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

    first-person singular pronouns and their contractions in informal conversational text.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Negative Logits
     Photocase
    -0.54
    ArrowToggle
    -0.50
     ModelExpression
    -0.50
     Wicidata
    -0.49
    scriptcase
    -0.49
    XmlAccessType
    -0.49
    hasMoreElements
    -0.49
    EReference
    -0.49
     būtų
    -0.48
    calientes
    -0.47
    POSITIVE LOGITS
     ihn
    0.82
     him
    0.82
     them
    0.66
     se
    0.65
    them
    0.60
     honom
    0.60
     sobie
    0.59
     us
    0.54
     sich
    0.52
     ihm
    0.52
    Act Density 0.104%

    No Known Activations