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

    Neuronpedia

    INDEX
    Explanations

    instances of actions or events occurring at a later time

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "later."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mad
    -0.74
    Ble
    -0.73
    ignment
    -0.69
     Pwr
    -0.69
    hab
    -0.65
    lua
    -0.64
    ampa
    -0.63
    TO
    -0.62
     Wish
    -0.61
    toe
    -0.61
    POSITIVE LOGITS
     regretted
    0.84
    iations
    0.80
     confir
    0.77
     succumb
    0.76
     succumbed
    0.76
     deleted
    0.75
     obser
    0.75
    ally
    0.74
     iterations
    0.74
     recons
    0.74
    Act Density 0.031%

    No Known Activations