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

    Neuronpedia

    INDEX
    Explanations

    references to criminal acts involving minors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     СеÑĢед
    -0.15
    antar
    -0.15
    arest
    -0.15
    anken
    -0.15
    ailable
    -0.14
    ",__
    -0.14
    ãģ¡ãĤĥ
    -0.14
    -www
    -0.14
    ãģªãĤĵãģ¦
    -0.14
    çı
    -0.13
    POSITIVE LOGITS
     allegedly
    0.17
     approximately
    0.15
    约
    0.14
    useppe
    0.14
    Approx
    0.14
     Fac
    0.14
    loth
    0.13
    ILLISE
    0.13
    ез
    0.13
     repeatedly
    0.13
    Act Density 0.192%

    No Known Activations