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

    Neuronpedia

    INDEX
    Explanations

    filenames containing the word "bat"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "bat" or related variations in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     MN
    -0.73
     RL
    -0.70
     Finnish
    -0.64
     Food
    -0.64
     labels
    -0.63
     networks
    -0.62
     structure
    -0.61
    ãģª
    -0.61
     implemented
    -0.60
     reversed
    -0.60
    POSITIVE LOGITS
    bat
    4.65
    bats
    2.72
    BAT
    1.95
    Bat
    1.87
     bat
    1.54
     Bat
    1.42
    cat
    1.19
    cham
    1.08
    bet
    1.07
     BAT
    1.04
    Act Density 0.009%

    No Known Activations