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

    Neuronpedia

    INDEX
    Explanations

    phrases referring to sets or collections of items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ftance
    -0.97
    couvrez
    -0.87
    ftances
    -0.85
    voorbeeld
    -0.85
    SerializedSize
    -0.84
    RESP
    -0.79
     carab
    -0.78
    Искәрмәләр
    -0.77
    Weiterlesen
    -0.75
    OfBirth
    -0.75
    POSITIVE LOGITS
     set
    1.64
     SET
    1.57
     Set
    1.56
    set
    1.54
    Set
    1.53
     sets
    1.38
    SET
    1.37
     Sets
    1.33
    sets
    1.22
     Seton
    1.19
    Act Density 0.119%

    No Known Activations