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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "mod" and related terms indicating modularity or module structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     zijne
    -0.61
     engraçadas
    -0.55
     dezelve
    -0.54
     zelve
    -0.53
    aronder
    -0.52
     mijne
    -0.51
     scattata
    -0.50
     kautta
    -0.49
    jenige
    -0.48
     epä
    -0.48
    POSITIVE LOGITS
     Mod
    1.63
    mod
    1.59
     mod
    1.59
    Mod
    1.52
     modulation
    1.26
     Moder
    1.26
    Moder
    1.24
     modulate
    1.23
     Mods
    1.21
     modulated
    1.21
    Act Density 0.213%

    No Known Activations