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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate possession or affiliation

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

    any of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ọa
    -0.47
    Билгалдахарш
    -0.47
    Autoritní
    -0.46
    '])){
    -0.45
    temon
    -0.44
     propOrder
    -0.43
     hohem
    -0.43
    tant
    -0.43
    AutoScale
    -0.42
    PropertyChanging
    -0.42
    POSITIVE LOGITS
     any
    0.81
     quelconque
    0.79
     cualquiera
    0.68
     quaisquer
    0.66
     anything
    0.65
     qualquer
    0.64
     whatsoever
    0.63
    Any
    0.62
     Any
    0.62
     quelcon
    0.60
    Act Density 0.012%

    No Known Activations