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

    Neuronpedia

    INDEX
    Explanations

    repeated uses of the word "same"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     wireType
    -0.72
    MultipartFile
    -0.58
     spinners
    -0.57
    ък
    -0.54
     interessiert
    -0.54
    PMailer
    -0.53
    raco
    -0.51
    isFile
    -0.50
     naselje
    -0.50
    données
    -0.50
    POSITIVE LOGITS
     same
    1.18
    same
    1.07
    Same
    1.07
     Same
    1.00
     SAME
    0.99
    SAME
    0.98
     samma
    0.89
     hetzelfde
    0.79
     dasselbe
    0.79
    zelfde
    0.76
    Act Density 0.135%

    No Known Activations