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

    Neuronpedia

    INDEX
    Explanations

    references to unfinished tasks or items in code, particularly related to properties and inheritance structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    leih
    -0.52
     старости
    -0.51
     '{@
    -0.49
    ("*");
    -0.46
     parques
    -0.46
    릎
    -0.45
     costas
    -0.45
     sogget
    -0.45
     SearchView
    -0.44
    <bos>
    -0.44
    POSITIVE LOGITS
    unfinished
    4.50
     unfinished
    2.58
    Unfinished
    2.04
    未完
    1.24
     incomplete
    1.22
    incomplete
    1.17
    finished
    1.11
    FINISHED
    1.06
    Incomplete
    1.05
     Incomplete
    1.04
    Act Density 0.005%

    No Known Activations