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

    Neuronpedia

    INDEX
    Explanations

    self-referential expressions and discussions of personal traits

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    XmlAccessorType
    -0.57
    LookAnd
    -0.56
    setVerticalGroup
    -0.53
     endblock
    -0.50
    GEBURTS
    -0.46
    outSlope
    -0.43
     "..\..\
    -0.42
    RegistryLite
    -0.42
    BeginContext
    -0.41
     pite
    -0.41
    POSITIVE LOGITS
     loves
    1.17
     hates
    1.10
     prefers
    1.05
     likes
    1.04
     prefer
    0.99
     love
    0.96
     tend
    0.94
     tends
    0.93
    loves
    0.93
     tendency
    0.92
    Act Density 0.432%

    No Known Activations