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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "same" in various contexts, particularly when discussing shared experiences or problems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    indicates sameness of problem or outcome

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dezelve
    -0.52
     vermogen
    -0.51
    Herzliche
    -0.50
     boste
    -0.49
     keduanya
    -0.49
     zoude
    -0.49
     niitä
    -0.48
    Manfaat
    -0.48
     sitä
    -0.47
     Angebote
    -0.47
    POSITIVE LOGITS
     للمعارف
    0.51
    VolleyError
    0.48
     Worst
    0.44
    worse
    0.42
    xmlhttp
    0.42
    worst
    0.42
     ugli
    0.40
    UserScript
    0.39
    Worst
    0.39
     worst
    0.39
    Act Density 0.030%

    No Known Activations