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

    Neuronpedia

    INDEX
    Explanations

    phrases related to past events or occurrences

    oai_token-act-pair · gpt-3.5-turbo

    instances of events or incidents that have occurred

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     abstract
    -0.54
     interchangeable
    -0.53
    earable
    -0.53
     solitude
    -0.53
     dou
    -0.53
     handmade
    -0.52
    ictionary
    -0.52
    ographies
    -0.52
    Written
    -0.52
    iles
    -0.51
    POSITIVE LOGITS
     recently
    0.82
     here
    0.78
     last
    0.77
     yesterday
    0.75
     during
    0.74
     happen
    0.72
    iasco
    0.72
     happened
    0.72
     elsewhere
    0.72
     earlier
    0.71
    Act Density 0.238%

    No Known Activations