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

    Neuronpedia

    INDEX
    Explanations

    quoted strings or characters in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    "])
    -0.81
    '}),
    -0.81
    contentLoaded
    -0.79
    '},
    -0.78
     CreateTagHelper
    -0.77
    "})
    -0.75
    "</
    -0.73
     Paglinawan
    -0.72
    "):
    -0.72
    '):
    -0.71
    POSITIVE LOGITS
    יוחד
    0.65
     Yer
    0.63
    ├──
    0.62
    <th>
    0.57
     שוליים
    0.57
     Nij
    0.57
    └──
    0.57
    tır
    0.55
    Ừ
    0.54
    roster
    0.54
    Act Density 0.084%

    No Known Activations