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

    Neuronpedia

    INDEX
    Explanations

    references to the word "the" and its vicinity within sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    RenderAtEndOf
    -0.59
    Personensuche
    -0.55
    rungsseite
    -0.54
     चीज़ों
    -0.51
    Autoritní
    -0.48
     enää
    -0.46
    Спољашње
    -0.46
    hyrchwyd
    -0.42
    Espèce
    -0.41
    fillType
    -0.41
    POSITIVE LOGITS
     thereto
    0.60
     toward
    0.59
     towards
    0.59
     into
    0.57
    到
    0.53
     unto
    0.52
     onto
    0.50
     to
    0.50
    tothe
    0.49
     INTO
    0.47
    Act Density 0.275%

    No Known Activations