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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "through."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    RenderAtEndOf
    -0.75
    vanje
    -0.62
     متعلقه
    -0.58
     marinho
    -0.55
     précédentes
    -0.53
     autorités
    -0.52
     chrétiens
    -0.51
     seguido
    -0.51
     précédents
    -0.51
    isation
    -0.50
    POSITIVE LOGITS
    ogh
    1.05
    puts
    0.98
    THROUGH
    0.86
    through
    0.85
    HOUT
    0.82
    tagHelperRunner
    0.77
     hoops
    0.77
    Through
    0.76
     intermedi
    0.76
    oughly
    0.75
    Act Density 0.107%

    No Known Activations