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

    Neuronpedia

    INDEX
    Explanations

    specific grammatical elements and structures in sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Interventions
    -0.43
    qvarna
    -0.42
    mobileqq
    -0.41
    rtl
    -0.37
    Diwedd
    -0.37
    DJANGO
    -0.36
     Llew
    -0.36
     yyb
    -0.36
     esca
    -0.36
     Tapia
    -0.35
    POSITIVE LOGITS
    ungs
    0.79
    ung
    0.62
    bare
    0.61
    ungen
    0.59
    UNG
    0.54
     pinulongan
    0.51
    ungsver
    0.50
     Numerade
    0.48
    bar
    0.48
    ende
    0.47
    Act Density 0.134%

    No Known Activations