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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating contrast or exceptions in information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aarrggbb
    -0.66
     ivelany
    -0.57
     ardından
    -0.56
    InitVars
    -0.56
    rrggbb
    -0.55
    一種
    -0.53
     verschiedener
    -0.53
    ]++;
    -0.53
     sekaligus
    -0.53
    зулта
    -0.51
    POSITIVE LOGITS
     few
    1.82
    Few
    1.66
    few
    1.58
     Few
    1.57
     nobody
    1.51
     none
    1.47
     hardly
    1.40
     FEW
    1.29
     pocos
    1.25
     neither
    1.23
    Act Density 0.660%

    No Known Activations