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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the sequence of past events

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to recent events or performance in sports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    conom
    -0.63
     Tanz
    -0.61
    progress
    -0.57
    Progress
    -0.56
    clerosis
    -0.55
    hyde
    -0.54
    illation
    -0.53
     Protection
    -0.53
    edu
    -0.52
    mund
    -0.52
    POSITIVE LOGITS
     three
    1.27
     four
    1.26
     two
    1.23
     five
    1.18
     seven
    1.16
     eight
    1.15
     nine
    1.13
    three
    1.10
     six
    1.08
     THREE
    1.04
    Act Density 0.091%

    No Known Activations