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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate a call to action or suggestions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Hüs
    -0.18
    iedo
    -0.18
    ngine
    -0.16
     Bảo
    -0.15
    egas
    -0.15
     ÑĤов
    -0.15
    ÑĥлÑİ
    -0.15
    usk
    -0.15
    culo
    -0.14
    verity
    -0.14
    POSITIVE LOGITS
    enn
    0.15
    Inset
    0.14
     Kore
    0.14
    rides
    0.14
     parc
    0.14
    ent
    0.14
     works
    0.13
     пом
    0.13
     merits
    0.13
    inx
    0.13
    Act Density 0.184%

    No Known Activations