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

    Neuronpedia

    INDEX
    Explanations

    references to compliance and security standards in technology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .synthetic
    -0.15
    IGHL
    -0.15
    jan
    -0.15
    errer
    -0.15
    tings
    -0.14
     undisclosed
    -0.14
     zaj
    -0.14
    acas
    -0.14
    .deb
    -0.14
     IDb
    -0.14
    POSITIVE LOGITS
     controls
    0.22
     Controls
    0.21
    Controls
    0.19
    _controls
    0.18
    controls
    0.18
     PCI
    0.16
    cio
    0.16
    elden
    0.16
    -controls
    0.16
    atts
    0.16
    Act Density 0.008%

    No Known Activations