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

    Neuronpedia

    INDEX
    Explanations

    words and phrases indicating quality or evaluation of objects or experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    juan
    -0.18
     swe
    -0.16
     sweat
    -0.16
    plet
    -0.16
     itemprop
    -0.16
     Swe
    -0.16
    .criteria
    -0.15
    rb
    -0.15
    öm
    -0.14
    pler
    -0.13
    POSITIVE LOGITS
    anchors
    0.17
    udden
    0.16
    ë²Į
    0.16
    mens
    0.16
     tem
    0.16
     TEM
    0.15
    ünchen
    0.14
    yk
    0.14
    '][]
    0.14
    оÑĢе
    0.14
    Act Density 0.006%

    No Known Activations