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

    Neuronpedia

    INDEX
    Explanations

    instances of the prefix "re-" indicating repetition or returning actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     виправивши
    -0.39
    GNUC
    -0.35
     doute
    -0.35
    fertigen
    -0.34
     ſche
    -0.34
    อา
    -0.34
     Kamil
    -0.33
    reicht
    -0.33
     wisdom
    -0.33
    plain
    -0.33
    POSITIVE LOGITS
     re
    0.77
    GOTREF
    0.57
     autorytatywna
    0.54
    MLLoader
    0.52
     createContext
    0.50
     rew
    0.49
    configure
    0.47
     res
    0.47
    новништво
    0.47
     ree
    0.46
    Act Density 0.221%

    No Known Activations