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

    Neuronpedia

    INDEX
    Explanations

    phrases and conjunctions that connect ideas in a sentence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     duk
    -0.15
    ingham
    -0.15
     fatt
    -0.14
    太éĥİ
    -0.14
    blas
    -0.14
    ãĤ¹ãĤ«
    -0.14
     fou
    -0.14
    heimer
    -0.14
    -transitional
    -0.14
     adher
    -0.14
    POSITIVE LOGITS
    GO
    0.20
     play
    0.19
     shoot
    0.18
     fly
    0.18
     GO
    0.18
    -go
    0.17
    eya
    0.17
     go
    0.17
     Play
    0.16
     eat
    0.16
    Act Density 0.058%

    No Known Activations