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

    Neuronpedia

    INDEX
    Explanations

    instances where individuals could not be reached for comments or responses

    oai_token-act-pair · gpt-3.5-turbo

    the verb "be" in various forms and contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    izable
    -0.72
     Manufact
    -0.67
     Wid
    -0.67
     TOD
    -0.65
     fray
    -0.62
     Struggle
    -0.61
     attempt
    -0.61
     Acquisition
    -0.61
     Ply
    -0.61
     LW
    -0.59
    POSITIVE LOGITS
     bothered
    1.11
     persuaded
    1.03
     trusted
    1.02
     forgiven
    0.98
     relied
    0.94
    amed
    0.94
     counted
    0.92
     swayed
    0.92
     sure
    0.90
     assured
    0.88
    Act Density 0.058%

    No Known Activations