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

    Neuronpedia

    INDEX
    Explanations

    words related to 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
    ersive
    -0.78
    ufact
    -0.78
     absentee
    -0.76
    nea
    -0.71
    EMA
    -0.70
     Parables
    -0.67
    Wr
    -0.67
    ISA
    -0.66
    States
    -0.66
    uthor
    -0.64
    POSITIVE LOGITS
    lake
    0.98
    bags
    0.97
    mith
    0.94
     rocks
    0.93
    bag
    0.87
    frog
    0.79
    creen
    0.79
    anguage
    0.78
    wagen
    0.78
    walker
    0.76
    Act Density 0.016%

    No Known Activations