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

    Neuronpedia

    INDEX
    Explanations

    special character sequences or patterns in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     تضيفلها
    -0.99
    endphp
    -0.97
    脚注の使い方
    -0.95
     CreateTagHelper
    -0.91
    TagMode
    -0.82
     للمعارف
    -0.81
    BeginContext
    -0.79
    UnusedPrivate
    -0.76
    principalTable
    -0.75
    Hentet
    -0.73
    POSITIVE LOGITS
     B
    0.47
     A
    0.47
    9
    0.43
    A
    0.42
    B
    0.38
    b
    0.38
     Verteilung
    0.36
     obligé
    0.36
     बी
    0.35
    stram
    0.35
    Act Density 0.196%

    No Known Activations