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

    Neuronpedia

    INDEX
    Explanations

    words related to "rel"

    oai_token-act-pair · gpt-3.5-turbo

    references to relationships or relational concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    HAEL
    -0.89
    FACE
    -0.74
    ĺħ
    -0.63
    BOX
    -0.63
    displayText
    -0.60
     mortal
    -0.57
    ItemImage
    -0.57
    URE
    -0.57
    MET
    -0.56
     heaven
    -0.56
    POSITIVE LOGITS
    igion
    1.26
    iability
    1.12
    iance
    1.10
    iever
    1.09
    ief
    1.06
    iable
    1.04
    iably
    0.99
    ieved
    0.98
    inqu
    0.98
    ights
    0.96
    Act Density 0.006%

    No Known Activations