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

    Neuronpedia

    INDEX
    Explanations

    numerical figures in a specific range

    oai_token-act-pair · gpt-3.5-turbo

    numerical values and statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    advant
    -0.77
    atorial
    -0.67
    rade
    -0.62
    eus
    -0.62
    FACE
    -0.59
    arton
    -0.59
    Else
    -0.58
    cone
    -0.57
    INGTON
    -0.56
    ±
    -0.55
    POSITIVE LOGITS
    %.
    1.15
     apiece
    1.03
    %,
    1.03
    %;
    0.92
     per
    0.85
     tonnes
    0.82
     units
    0.81
    kb
    0.80
     litres
    0.80
    +.
    0.79
    Act Density 0.188%

    No Known Activations