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

    Neuronpedia

    INDEX
    Explanations

    words indicating scarcity or minimal presence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    terscotch
    -0.60
    downarrow
    -0.58
     foramen
    -0.58
     revanche
    -0.56
    billon
    -0.56
    ILON
    -0.55
    IDEA
    -0.55
    idemia
    -0.55
    setCharacter
    -0.53
    gite
    -0.53
    POSITIVE LOGITS
     hardly
    2.42
     barely
    2.27
     Hardly
    2.25
     scarcely
    1.96
     kaum
    1.26
     rarely
    1.11
     едва
    1.11
     barley
    1.05
     guère
    1.04
     seldom
    1.00
    Act Density 0.122%

    No Known Activations