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

    Neuronpedia

    INDEX
    Explanations

    words related to animals

    oai_token-act-pair · gpt-3.5-turbo

    token endings or sentence delimiters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iferation
    -0.81
    )=(
    -0.77
    Interstitial
    -0.76
     condem
    -0.75
    oppable
    -0.73
     Palestin
    -0.70
    ISTER
    -0.69
     tert
    -0.69
     proport
    -0.68
    mberg
    -0.67
    POSITIVE LOGITS
    fish
    1.24
    tailed
    1.22
    ishly
    1.12
    frog
    1.09
    bear
    1.07
     carc
    1.01
    hawk
    1.01
     owl
    0.98
    toe
    0.98
    hole
    0.98
    Act Density 0.148%

    No Known Activations