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

    Neuronpedia

    INDEX
    Explanations

    instances of representation and honor in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    دانشنامهٔ
    -0.51
    jarat
    -0.40
    Życiorys
    -0.39
     mortal
    -0.38
     صوتيه
    -0.37
     vaz
    -0.36
    irvana
    -0.36
    Liked
    -0.36
     CreateTagHelper
    -0.34
     ruth
    -0.34
    POSITIVE LOGITS
     representan
    0.68
     representing
    0.64
     representation
    0.62
    representing
    0.62
     representar
    0.60
     reprezent
    0.60
     Representing
    0.59
     representación
    0.59
     représentation
    0.57
    Represent
    0.57
    Act Density 0.252%

    No Known Activations