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

    Neuronpedia

    INDEX
    Explanations

    phrases related to being the first or one of a kind

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate the first instance or occurrence of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lees
    -0.73
    matter
    -0.72
    zeb
    -0.72
    desktop
    -0.58
    istine
    -0.58
     throne
    -0.57
    hr
    -0.57
    atche
    -0.57
     babys
    -0.56
    "},{"
    -0.55
    POSITIVE LOGITS
     several
    1.48
     dozens
    1.35
     many
    1.32
     numerous
    1.23
     countless
    1.22
     innumerable
    1.22
     hundreds
    1.21
     three
    1.21
    sever
    1.18
     four
    1.16
    Act Density 0.110%

    No Known Activations