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

    Neuronpedia

    INDEX
    Explanations

    mentions of rocks

    oai_token-act-pair · gpt-3.5-turbo

    references to rocks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    present
    -0.71
    Wr
    -0.70
    EMA
    -0.68
    åĬ
    -0.67
    æ©Ł
    -0.67
    Clar
    -0.67
    ersive
    -0.66
    nec
    -0.66
    ufact
    -0.66
    Myth
    -0.65
    POSITIVE LOGITS
     rocks
    1.06
    lake
    0.98
    mith
    0.95
     bould
    0.86
    bags
    0.85
     rock
    0.78
    frog
    0.78
    bag
    0.77
    creen
    0.76
    melon
    0.76
    Act Density 0.018%

    No Known Activations