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

    Neuronpedia

    INDEX
    Explanations

    phrases or terms related to first occurrences or initial experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ixa
    -0.18
     first
    -0.18
    ixo
    -0.17
    rzy
    -0.16
     further
    -0.16
     forth
    -0.15
     firstly
    -0.15
    essler
    -0.15
    cken
    -0.15
    dal
    -0.15
    POSITIVE LOGITS
    -ever
    0.38
    s
    0.34
     tiên
    0.30
    -hand
    0.29
    -rate
    0.29
    born
    0.28
     timers
    0.25
    -order
    0.25
     responders
    0.24
    -time
    0.24
    Act Density 0.130%

    No Known Activations