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

    Neuronpedia

    INDEX
    Explanations

    instances of bolded text elements in the document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    帖最后由
    -0.72
     ویکی‌پدی
    -0.59
    DIPSETTING
    -0.59
    -------------</
    -0.57
    ---*/
    -0.56
    点此举报
    -0.56
    AddTagHelper
    -0.56
    DebuggerNonUser
    -0.51
     Picchu
    -0.51
    loài
    -0.49
    POSITIVE LOGITS
    </strong>
    1.11
    </b>
    0.91
    )");
    0.63
     itſelf
    0.61
    ')")
    0.60
    )');
    0.57
     ſche
    0.57
    ſelf
    0.55
    GetHashCode
    0.55
    gaard
    0.52
    Act Density 0.048%

    No Known Activations