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

    Neuronpedia

    INDEX
    Explanations

    phrases or words indicating something that has recently changed or been introduced

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

    the word "newly" appearing before adjectives or past participles.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Negative Logits
    IPPING
    -0.40
    وردار
    -0.39
     negócios
    -0.38
     darb
    -0.38
     ägg
    -0.37
     solchen
    -0.37
     Sommers
    -0.36
     spéciaux
    -0.35
    bringing
    -0.34
    してしまう
    -0.34
    POSITIVE LOGITS
     المعيارى
    0.76
     installed
    0.73
     acquired
    0.73
     discovered
    0.71
    RegressionTest
    0.69
     downloaded
    0.69
     implemented
    0.68
     recorded
    0.68
     created
    0.67
     adopted
    0.66
    Act Density 0.330%

    No Known Activations