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

    Neuronpedia

    INDEX
    Explanations

    discussions or references to differences and comparisons between concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ModelAdmin
    -0.70
    ChildScrollView
    -0.69
    ">:
    -0.62
     poussière
    -0.62
    นี่
    -0.61
    ண்டும்
    -0.61
     digitais
    -0.61
    SDAY
    -0.60
     vidare
    -0.59
     zustand
    -0.58
    POSITIVE LOGITS
     DIF
    0.84
     Diff
    0.83
     between
    0.83
     Dif
    0.81
    DIF
    0.79
     AssemblyCulture
    0.76
    Diff
    0.71
    between
    0.70
     diff
    0.69
     DIFFERENCE
    0.68
    Act Density 0.276%

    No Known Activations