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

    Neuronpedia

    INDEX
    Explanations

    phrases relating to the length of time someone has been in a particular role or position

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the duration of time spent in various roles or positions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ussed
    -0.68
    hod
    -0.68
     Mane
    -0.67
    iqu
    -0.65
    upiter
    -0.65
    annis
    -0.64
    ople
    -0.63
    react
    -0.63
    Gre
    -0.62
    antam
    -0.61
    POSITIVE LOGITS
     ago
    1.16
     olds
    0.88
     Ago
    0.80
     spanning
    0.76
     since
    0.71
     uninterrupted
    0.70
    worth
    0.70
    ãĥ»
    0.70
     old
    0.67
     consecut
    0.66
    Act Density 0.108%

    No Known Activations