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

    Neuronpedia

    INDEX
    Explanations

    elements related to safety and security

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    moveToFirst
    -0.62
     snippetHide
    -0.62
    AndEndTag
    -0.59
     présidenti
    -0.56
    ftagPool
    -0.55
     AssemblyCompany
    -0.55
     polaire
    -0.54
    ENDIAN
    -0.54
     chinoise
    -0.54
     japonaise
    -0.52
    POSITIVE LOGITS
    ny
    0.66
    naya
    0.59
    ный
    0.56
    ное
    0.54
     NUKAT
    0.52
    ные
    0.51
    ný
    0.51
     indirect
    0.51
    ní
    0.50
    ная
    0.49
    Act Density 0.064%

    No Known Activations