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

    Neuronpedia

    INDEX
    Explanations

    phrases or sentences ending with a question mark

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of a specific character or symbol

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Buyable
    -0.71
    seed
    -0.68
    ctors
    -0.66
     Mun
    -0.64
     Mansion
    -0.61
     shack
    -0.60
     Trip
    -0.59
     Opera
    -0.59
     hob
    -0.59
    è£ħ
    -0.58
    POSITIVE LOGITS
    £
    0.98
    º
    0.87
    ¬
    0.83
    Ĵ
    0.82
    ¡
    0.82
    ¼
    0.82
    ¹
    0.80
    ought
    0.76
    ½
    0.76
    ı
    0.75
    Act Density 0.051%

    No Known Activations