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

    Neuronpedia

    INDEX
    Explanations

    terms indicating authority or control

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    avanaugh
    -0.16
    bach
    -0.16
    undra
    -0.15
    ucket
    -0.15
    _TUN
    -0.15
    гал
    -0.15
    GU
    -0.14
     Civic
    -0.14
     Tun
    -0.14
    kas
    -0.14
    POSITIVE LOGITS
    alers
    0.17
    reeze
    0.16
    aro
    0.16
    åı°
    0.15
    oya
    0.15
    ists
    0.15
    ecut
    0.14
    ед
    0.14
    stdafx
    0.14
    sted
    0.14
    Act Density 0.032%

    No Known Activations