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

    Neuronpedia

    INDEX
    Explanations

    the word "I" and related personal pronouns used in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    就不会
    -0.63
    ValueStyle
    -0.61
    béco
    -0.59
    writeFieldEnd
    -0.56
    DockStyle
    -0.55
     виправивши
    -0.55
     ExecuteAsync
    -0.55
    s
    -0.53
    就没
    -0.53
    存于互联网档案馆
    -0.53
    POSITIVE LOGITS
    我
    1.45
    他
    1.41
    你
    1.40
    我们
    1.16
    她
    1.09
     我
    0.97
    其
    0.92
    他们
    0.91
     你
    0.91
    我們
    0.90
    Act Density 0.084%

    No Known Activations