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

    Neuronpedia

    INDEX
    Explanations

    phrases related to significant events or changes happening for the first time

    oai_token-act-pair · gpt-3.5-turbo

    references to significant experiences or moments denoting "first times."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    buster
    -0.68
    ibr
    -0.67
    conn
    -0.67
    Conn
    -0.66
    Cho
    -0.65
    peer
    -0.65
    venants
    -0.63
    agree
    -0.63
    mare
    -0.61
    Enjoy
    -0.59
    POSITIVE LOGITS
     sake
    1.79
     purposes
    1.40
     remainder
    1.25
     foreseeable
    1.22
     upcoming
    1.12
     same
    1.11
     purpose
    1.07
     reasons
    1.06
     entirety
    1.06
     duration
    0.98
    Act Density 0.208%

    No Known Activations