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

    Neuronpedia

    INDEX
    Explanations

    references to frogs

    oai_token-act-pair · gpt-3.5-turbo

    references to frogs and amphibians

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Interstitial
    -0.77
    Definition
    -0.70
    ×ij
    -0.67
    å¦
    -0.64
     Parenthood
    -0.64
    tumblr
    -0.63
    HC
    -0.62
    CLA
    -0.61
     Hemp
    -0.60
    ×Ļ
    -0.60
    POSITIVE LOGITS
     frogs
    1.23
     frog
    1.18
    grass
    1.02
    frog
    1.00
    lings
    0.94
    fish
    0.90
     Frog
    0.88
    adier
    0.86
    brate
    0.86
    mons
    0.84
    Act Density 0.005%

    No Known Activations