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

    Neuronpedia

    INDEX
    Explanations

    phrases associated with protection and security

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Emer
    -0.15
    erg
    -0.15
    sher
    -0.14
    apas
    -0.13
     artificial
    -0.13
     Elk
    -0.13
    ãģĵãĤĵ
    -0.13
     informed
    -0.13
    ANEL
    -0.13
    atri
    -0.13
    POSITIVE LOGITS
     protection
    0.15
    à¹Ĥà¸Ĭ
    0.14
     drafts
    0.14
    .staff
    0.14
     unprotected
    0.14
     ÑĢаÑģÑĩ
    0.14
    олиÑĤ
    0.14
     disb
    0.13
    upro
    0.13
     protects
    0.13
    Act Density 0.099%

    No Known Activations