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

    Neuronpedia

    INDEX
    Explanations

    phrases related to origins or beginnings of concepts or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     setState
    -0.74
     Metz
    -0.71
    </b>
    -0.70
    </i>
    -0.69
    kesha
    -0.67
    owulf
    -0.67
     Monza
    -0.66
    Chham
    -0.66
    arashtra
    -0.64
     Cowper
    -0.62
    POSITIVE LOGITS
     origin
    1.57
     Origin
    1.56
     origins
    1.54
     Origins
    1.52
    Origin
    1.48
    Origins
    1.43
    origin
    1.42
     originates
    1.40
     ORIGIN
    1.37
    origins
    1.31
    Act Density 0.177%

    No Known Activations