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

    Neuronpedia

    INDEX
    Explanations

    mentions of virtual addresses or networks

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    éĹĺ
    -0.73
    heet
    -0.72
    hirt
    -0.71
    inventoryQuantity
    -0.69
    ered
    -0.68
    agher
    -0.68
    cake
    -0.67
    unct
    -0.67
    ursed
    -0.67
    FontSize
    -0.67
    POSITIVE LOGITS
    ization
    1.14
    isation
    1.07
    ized
    1.07
     reality
    1.06
    reality
    1.04
    izable
    0.94
    izing
    0.94
     Reality
    0.93
     worlds
    0.93
    isable
    0.89
    Act Density 0.021%

    No Known Activations