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

    Neuronpedia

    INDEX
    Explanations

    instances of proper nouns, particularly names and titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    しまった
    -0.71
    ۰۰
    -0.70
    ください
    -0.67
     autorytatywna
    -0.63
    жидан
    -0.58
    ième
    -0.54
    しまう
    -0.53
    ました
    -0.53
    ként
    -0.51
     NSCoder
    -0.51
    POSITIVE LOGITS
     
    0.48
    jména
    0.37
    aa
    0.37
    olk
    0.35
    ある
    0.35
    ade
    0.35
    HtmlAttribute
    0.34
    charAt
    0.34
    pe
    0.34
    chat
    0.33
    Act Density 0.302%

    No Known Activations