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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "the" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     similarly
    -0.18
     Erotik
    -0.18
     podob
    -0.17
     simil
    -0.17
    аниÑĨ
    -0.16
    Similar
    -0.15
     Similar
    -0.15
    essler
    -0.15
    cision
    -0.15
    ngr
    -0.15
    POSITIVE LOGITS
     sam
    0.39
     same
    0.37
    same
    0.34
     même
    0.31
    sam
    0.31
     samo
    0.31
     sami
    0.30
     Sam
    0.28
     sane
    0.28
     sa
    0.27
    Act Density 0.044%

    No Known Activations