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

    Neuronpedia

    INDEX
    Explanations

    references to a type of greeting or excitement, particularly variations of "ho."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bers
    -0.19
    mente
    -0.18
    ut
    -0.16
    pu
    -0.15
    ners
    -0.15
    borg
    -0.15
    ον
    -0.15
    bur
    -0.14
    rael
    -0.14
    åı·
    -0.14
    POSITIVE LOGITS
    izontal
    0.20
    resh
    0.18
    isting
    0.18
     ho
    0.18
    iteli
    0.18
    ặc
    0.17
    Ho
    0.17
    tel
    0.17
    isted
    0.17
     Ho
    0.17
    Act Density 0.010%

    No Known Activations