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

    Neuronpedia

    INDEX
    Explanations

    financial and political entities or institutions

    oai_token-act-pair · gpt-3.5-turbo

    words that contain a specific Unicode character

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    odan
    -0.72
     pity
    -0.70
     scattering
    -0.69
    romy
    -0.67
     vom
    -0.66
     blond
    -0.65
     decomp
    -0.65
     jelly
    -0.64
    ussian
    -0.63
     maxim
    -0.63
    POSITIVE LOGITS
    £
    1.07
    ¬
    1.00
    ı
    0.95
    Asia
    0.94
    ¹
    0.93
    į
    0.90
    âĹ¼
    0.88
    Ĭ
    0.88
    Ĵ
    0.87
    ħ
    0.87
    Act Density 0.340%

    No Known Activations