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

    Neuronpedia

    INDEX
    Explanations

    phrases related to tides or controlling/turning forces

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    iator
    -1.04
    es
    -1.02
    iates
    -0.98
    ible
    -0.95
    edly
    -0.93
    iated
    -0.93
    iate
    -0.92
    ively
    -0.91
    IBLE
    -0.87
    ibility
    -0.87
    POSITIVE LOGITS
    fish
    0.87
    hower
    0.79
     tide
    0.71
     buoy
    0.70
     tails
    0.68
     beans
    0.66
    hammer
    0.66
     roll
    0.65
     Whale
    0.65
     gland
    0.65
    Act Density 0.132%

    No Known Activations