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

    Neuronpedia

    INDEX
    Explanations

    phrases relating to countries or cultural experiences

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "ura."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rodu
    -0.94
    mosp
    -0.90
    yright
    -0.89
    sonian
    -0.83
    tons
    -0.79
    regor
    -0.76
    oration
    -0.76
    insula
    -0.75
    ablishment
    -0.74
    oleon
    -0.73
    POSITIVE LOGITS
    BILITY
    0.85
     Mazda
    0.81
    ð
    0.81
    ÅŁ
    0.79
    ña
    0.73
    Äĩ
    0.73
    zza
    0.73
    ves
    0.73
     Zar
    0.72
    igi
    0.72
    Act Density 0.011%

    No Known Activations