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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate emphasis or strong assertions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Tos
    -0.17
    ulp
    -0.16
    lew
    -0.15
    rets
    -0.15
     éĻĪ
    -0.15
    ider
    -0.14
     Ben
    -0.14
     Bart
    -0.14
    adin
    -0.14
    _inline
    -0.14
    POSITIVE LOGITS
    pf
    0.20
    iah
    0.15
    raj
    0.15
     Lâm
    0.15
    кÑĥÑĤ
    0.15
     Pf
    0.14
    vý
    0.14
    sville
    0.14
    алом
    0.14
    hammer
    0.14
    Act Density 0.025%

    No Known Activations