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

    Neuronpedia

    INDEX
    Explanations

    numerical values representing indices or counters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    handleDelete
    -0.46
     Ansel
    -0.46
     juuri
    -0.46
     Barbier
    -0.45
     chien
    -0.44
     froze
    -0.43
    olto
    -0.43
    fate
    -0.43
    rocław
    -0.43
    चा
    -0.43
    POSITIVE LOGITS
     !=
    0.72
    !=
    0.70
    ReusableCell
    0.65
    <(
    0.64
     تضيفلها
    0.63
    ViewInit
    0.62
    <=
    0.61
     дописавши
    0.61
     <=
    0.60
    ++)
    0.57
    Act Density 0.081%

    No Known Activations