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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "first" and its related forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     first
    -0.16
    ixa
    -0.16
    ixin
    -0.15
    룡
    -0.15
    ths
    -0.15
    acs
    -0.15
    cken
    -0.15
    odesk
    -0.15
    ases
    -0.14
    thane
    -0.14
    POSITIVE LOGITS
    -ever
    0.34
    born
    0.29
    -rate
    0.28
    -hand
    0.27
     few
    0.25
     tiên
    0.25
     ever
    0.24
    -person
    0.24
     baseman
    0.23
    -order
    0.23
    Act Density 0.123%

    No Known Activations