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

    Neuronpedia

    INDEX
    Explanations

    references to societal or systemic failures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ourt
    -0.14
    edelta
    -0.14
    aat
    -0.14
    izmet
    -0.14
    embali
    -0.14
    _Impl
    -0.14
    åĭĻ
    -0.13
    ilities
    -0.13
    enu
    -0.13
    iously
    -0.13
    POSITIVE LOGITS
    /exp
    0.16
    ostel
    0.16
    à¥įà¤Łà¤®
    0.15
    ingly
    0.14
    dere
    0.14
    erty
    0.14
    ower
    0.14
     resort
    0.13
    ittel
    0.13
    WSC
    0.13
    Act Density 0.067%

    No Known Activations