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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating membership or association in a specific group

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    مقدمه
    -0.68
     okuyayım
    -0.67
    Encyklopedia
    -0.66
     виправивши
    -0.65
    достатки
    -0.64
     pageContext
    -0.62
     становника
    -0.62
    thschild
    -0.60
    sonaro
    -0.60
    ofition
    -0.60
    POSITIVE LOGITS
    UnusedPrivate
    0.70
    󠁿
    0.64
    帖最后由
    0.64
    ยว
    0.63
    thâu
    0.62
    withstanding
    0.60
    <bos>
    0.60
    Sucesor
    0.58
    DebuggerNonUser
    0.58
    سطس
    0.57
    Act Density 0.112%

    No Known Activations