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

    Neuronpedia

    INDEX
    Explanations

    words related to actions or events that involve a significant impact or transformation

    oai_token-act-pair · gpt-3.5-turbo

    words related to actions or movements in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     aisle
    -0.65
    FUN
    -0.61
    glass
    -0.61
     Contributions
    -0.60
    partisan
    -0.60
     Clause
    -0.59
     Notting
    -0.59
     chronological
    -0.58
     Straw
    -0.58
     Window
    -0.58
    POSITIVE LOGITS
    ifies
    0.97
    ersed
    0.95
    itates
    0.92
    tesy
    0.91
    inged
    0.89
    izes
    0.86
    isively
    0.85
    ared
    0.84
    iously
    0.82
    icated
    0.81
    Act Density 0.328%

    No Known Activations