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

    Neuronpedia

    INDEX
    Explanations

    phrases that evoke strong emotional responses or are contextually significant

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    conc
    -0.17
    .nlm
    -0.17
    uze
    -0.17
    uled
    -0.16
    esus
    -0.14
    vla
    -0.14
    ffen
    -0.14
    PIN
    -0.14
    loh
    -0.14
    Named
    -0.13
    POSITIVE LOGITS
    /or
    0.20
    iod
    0.15
    asser
    0.15
    acles
    0.15
    ifice
    0.15
    quirer
    0.14
    obi
    0.14
     Aires
    0.14
     downright
    0.13
     Retrofit
    0.13
    Act Density 0.063%

    No Known Activations