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

    Neuronpedia

    INDEX
    Explanations

    statements about facts and their correctness, often in a socio-political context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uyu
    -0.16
    ÏĦε
    -0.15
    ÅĽ
    -0.14
    rome
    -0.14
    ILLED
    -0.14
     Reputation
    -0.14
    uffers
    -0.14
     consort
    -0.14
     flourish
    -0.14
    von
    -0.14
    POSITIVE LOGITS
     importance
    0.29
     nature
    0.23
     Importance
    0.23
    import
    0.19
    nature
    0.18
     applic
    0.17
     role
    0.17
    elerik
    0.16
     import
    0.16
     univers
    0.16
    Act Density 0.230%

    No Known Activations