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

    Neuronpedia

    INDEX
    Explanations

    phrases related to reasons, motivations, and justifications

    oai_token-act-pair · gpt-3.5-turbo

    references to specific events or entities related to releases, studies, or surveys

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     cowork
    -0.56
    AppData
    -0.55
     annexed
    -0.55
    Joined
    -0.54
    phies
    -0.52
     consecut
    -0.51
    ById
    -0.50
    姫
    -0.50
     playable
    -0.49
    uthor
    -0.48
    POSITIVE LOGITS
     varies
    1.39
     depends
    1.38
     differs
    1.26
     lies
    1.20
     revolves
    1.15
     involves
    1.15
     is
    1.12
     rests
    1.11
     derives
    1.11
     consists
    1.06
    Act Density 0.293%

    No Known Activations