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

    Neuronpedia

    INDEX
    Explanations

    phrases related to recounting or expressing regret about past events

    oai_token-act-pair · gpt-3.5-turbo

    inquiries about events or actions that have occurred

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    etary
    -0.75
    claimer
    -0.71
    urations
    -0.69
    iscover
    -0.69
    izen
    -0.68
    uum
    -0.67
    enegger
    -0.65
    onomic
    -0.64
     scratch
    -0.64
    scan
    -0.59
    POSITIVE LOGITS
     transpired
    1.92
     happened
    1.85
     occurred
    1.48
     ensued
    1.38
     happ
    1.38
     happens
    1.35
     unfolded
    1.32
     Happ
    1.17
     awaited
    1.07
     awaits
    1.07
    Act Density 0.116%

    No Known Activations