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

    Neuronpedia

    INDEX
    Explanations

    phrases related to events or actions that are quickly approaching or being reached

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "approaching"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pite
    -0.96
    cell
    -0.84
    cake
    -0.80
    gans
    -0.74
    glass
    -0.73
    gae
    -0.72
    ford
    -0.70
    food
    -0.70
    fre
    -0.69
    band
    -0.69
    POSITIVE LOGITS
     Ceres
    0.89
     nearer
    0.69
     heights
    0.68
    isons
    0.65
     Lans
    0.64
     solicitation
    0.62
    ebin
    0.62
     halfway
    0.62
    heny
    0.61
    autions
    0.61
    Act Density 0.019%

    No Known Activations