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

    Neuronpedia

    INDEX
    Explanations

    passive voice phrases that might be related to formal announcements or reports

    oai_token-act-pair · gpt-3.5-turbo

    the word "been" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ette
    -0.60
    ooks
    -0.60
    ject
    -0.59
    Plot
    -0.59
    models
    -0.57
    iya
    -0.57
    ensing
    -0.57
    sets
    -0.53
    ism
    -0.52
    ule
    -0.52
    POSITIVE LOGITS
     been
    2.62
    been
    2.51
     Been
    2.07
     gotten
    1.82
     undergone
    1.55
     gone
    1.49
     begun
    1.47
     arisen
    1.35
     fallen
    1.31
     become
    1.28
    Act Density 0.131%

    No Known Activations