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

    Neuronpedia

    INDEX
    Explanations

    form variations of the verb "work."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    als
    -0.16
    uir
    -0.16
    /up
    -0.15
    xt
    -0.15
    uet
    -0.14
    oria
    -0.14
     Cres
    -0.14
    ars
    -0.14
    antha
    -0.14
    rek
    -0.14
    POSITIVE LOGITS
    bench
    0.19
    manship
    0.18
    stations
    0.18
    åĿĬ
    0.17
     harder
    0.15
    aday
    0.15
    nehmer
    0.15
    spaces
    0.15
    loads
    0.15
     wonders
    0.14
    Act Density 0.053%

    No Known Activations