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

    Neuronpedia

    INDEX
    Explanations

    references to vulnerable populations and issues related to health risks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     remainder
    -0.34
     rest
    -0.19
    remainder
    -0.18
     remaining
    -0.15
    icho
    -0.13
     Remaining
    -0.13
    antha
    -0.13
     entirety
    -0.13
    ../../../
    -0.13
     broader
    -0.12
    POSITIVE LOGITS
     most
    0.99
    most
    0.80
    æľĢ
    0.76
     MOST
    0.74
    -most
    0.73
     Most
    0.69
    _most
    0.67
     ê°Ģìŀ¥
    0.67
    Most
    0.67
    MOST
    0.65
    Act Density 1.267%

    No Known Activations