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

    Neuronpedia

    INDEX
    Explanations

    references to harmful or trivializing language regarding serious issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uard
    -0.15
     å¹
    -0.14
     Carrie
    -0.14
    opis
    -0.14
    ickers
    -0.14
    ispecies
    -0.14
    znik
    -0.13
    ect
    -0.13
    Aura
    -0.13
    /↵↵↵↵
    -0.13
    POSITIVE LOGITS
    ahir
    0.16
    theid
    0.15
    632
    0.14
     اÙĦتس
    0.14
    pery
    0.14
    ãģķãģĦ
    0.14
    /Dk
    0.14
    uede
    0.14
     TResult
    0.13
    ensi
    0.13
    Act Density 0.009%

    No Known Activations