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

    Neuronpedia

    INDEX
    Explanations

    code-related syntax or markup indicators

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    PreferredItem
    -1.05
     resourceCulture
    -1.02
    IUrlHelper
    -1.00
    principalColumn
    -0.96
     poffe
    -0.96
     ་་
    -0.94
     ſeveral
    -0.94
     ―――――
    -0.94
     Theſe
    -0.94
     Efq
    -0.94
    POSITIVE LOGITS
    {%
    0.70
    if
    0.63
     if
    0.61
    ↵↵
    0.56
    <?
    0.53
    czek
    0.51
     I
    0.49
    <eos>
    0.48
    ตัว
    0.48
     point
    0.48
    Act Density 0.085%

    No Known Activations