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

    Neuronpedia

    INDEX
    Explanations

    technical terms related to data structures and programming concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    帖最后由
    -0.93
     snippetHide
    -0.92
    UserScript
    -0.86
    ″]
    -0.83
     surla
    -0.79
     nakalista
    -0.79
     nahilalakip
    -0.74
    posedge
    -0.72
    swire
    -0.70
    InjectAttribute
    -0.69
    POSITIVE LOGITS
    1
    1.64
    2
    1.62
    3
    1.43
    4
    1.36
    5
    1.31
    6
    1.26
    7
    1.21
    9
    1.17
    8
    1.16
    0
    1.00
    Act Density 0.755%

    No Known Activations