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

    Neuronpedia

    INDEX
    Explanations

    personal names containing the substring "ks"

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of "Aks."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ø©
    -0.65
    ANN
    -0.62
    ption
    -0.60
    ت
    -0.60
     mosqu
    -0.60
     HE
    -0.59
     Rept
    -0.59
     pent
    -0.59
     surpr
    -0.57
     Vacc
    -0.55
    POSITIVE LOGITS
    crew
    1.48
    creen
    1.37
    ilver
    1.33
    wagen
    1.32
    andr
    1.31
    haw
    1.21
    hire
    1.16
    alid
    1.13
    onian
    1.04
    andra
    1.04
    Act Density 0.033%

    No Known Activations