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

    Neuronpedia

    INDEX
    Explanations

    words related to the action of releasing something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "released."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lasses
    -0.76
    izabeth
    -0.73
    rast
    -0.66
     Corinth
    -0.63
    typ
    -0.62
    ogeneity
    -0.61
    igans
    -0.60
     Twain
    -0.60
    mong
    -0.59
    esse
    -0.58
    POSITIVE LOGITS
     released
    3.51
    released
    2.84
     Released
    2.45
    Released
    2.41
     release
    2.40
     releases
    2.23
     releasing
    2.19
     Release
    2.04
    release
    1.91
    Release
    1.89
    Act Density 0.032%

    No Known Activations