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

    Neuronpedia

    INDEX
    Explanations

    descriptions or hypothetical scenarios where something has happened or could have happened

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express the concept of something that has already occurred or been done, often related to missed opportunities or past actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Deb
    -0.63
     Dj
    -0.60
    ftime
    -0.60
     now
    -0.58
     stump
    -0.57
     remix
    -0.57
     usually
    -0.57
     currently
    -0.56
    ness
    -0.56
    vec
    -0.55
    POSITIVE LOGITS
     sooner
    0.89
    Ire
    0.79
    LOCK
    0.72
    MpServer
    0.71
    anni
    0.70
    Title
    0.69
    iscons
    0.68
    TIT
    0.68
    ypes
    0.67
    1800
    0.66
    Act Density 0.140%

    No Known Activations