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

    Neuronpedia

    INDEX
    Explanations

    names of places

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     compensated
    -0.72
    ÏĢ
    -0.69
    ×ij
    -0.68
    ItemTracker
    -0.66
    ÄŁ
    -0.66
    Ĥª
    -0.65
    ׾
    -0.64
    hift
    -0.63
     cryst
    -0.63
     parity
    -0.63
    POSITIVE LOGITS
    ford
    1.14
    enberg
    1.13
    ley
    1.08
    strom
    1.08
    ued
    0.98
    mu
    0.96
    rams
    0.94
    ston
    0.93
    aroo
    0.92
    enstein
    0.92
    Act Density 0.025%

    No Known Activations