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

    Neuronpedia

    INDEX
    Explanations

    references to age differences in relationships

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

    Relationships indicating hierarchy or difference

    np_acts-logits-general · gemini-2.0-flash

    hierarchy and superiority

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    DoubleQuotes
    -0.69
    principalTable
    -0.67
    ServletException
    -0.63
     onAnimation
    -0.62
     integrand
    -0.60
    SharedCtor
    -0.57
    MessageTagHelper
    -0.57
    __);
    -0.55
     referenties
    -0.55
    eref
    -0.55
    POSITIVE LOGITS
     unequal
    0.84
     hierarchical
    0.69
     hierarchy
    0.64
     superiority
    0.59
    superior
    0.59
     disparity
    0.58
     autoridad
    0.57
     hierarchies
    0.56
     Superior
    0.56
     supervisory
    0.56
    Act Density 0.341%

    No Known Activations