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

    Neuronpedia

    INDEX
    Explanations

    phrases related to significant events or milestones

    oai_token-act-pair · gpt-3.5-turbo

    instances of significant events or milestones being described

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yre
    -0.70
     appre
    -0.65
    oir
    -0.64
    arak
    -0.64
     dstg
    -0.63
    inia
    -0.61
    urus
    -0.61
     hurled
    -0.60
     fortune
    -0.60
    æ©Ł
    -0.59
    POSITIVE LOGITS
     milestones
    0.89
    downs
    0.82
    manship
    0.81
     Twain
    0.81
     marking
    0.77
    down
    0.75
    mast
    0.73
    erness
    0.72
    break
    0.72
    stakes
    0.69
    Act Density 0.049%

    No Known Activations