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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate a change or impact, particularly those involving the word "make."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     يتيمه
    -0.61
     دیکھیے
    -0.48
     мәкал
    -0.47
    Jeografia
    -0.47
     ditangkap
    -0.46
    bootstrapcdn
    -0.46
    thâu
    -0.44
     pož
    -0.44
    rari
    -0.43
     rapides
    -0.43
    POSITIVE LOGITS
    makes
    0.52
    Makes
    0.49
     makes
    0.48
     Makes
    0.47
    addComponent
    0.43
     goose
    0.40
     MAKES
    0.39
     make
    0.39
    feels
    0.39
     autorytatywna
    0.38
    Act Density 0.103%

    No Known Activations