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

    Neuronpedia

    INDEX
    Explanations

    words related to significant mathematical concepts and terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Mansfield
    -0.83
    djangoproject
    -0.79
     Morde
    -0.72
     Zur
    -0.66
     Faul
    -0.65
     Horv
    -0.64
    sidemargin
    -0.63
     Langford
    -0.63
     Horton
    -0.63
     Sop
    -0.63
    POSITIVE LOGITS
     Mooney
    0.98
     Moo
    0.92
     Steen
    0.89
     Moos
    0.89
    Moo
    0.88
    moo
    0.87
     Saar
    0.85
     moo
    0.85
    apollo
    0.85
     carottes
    0.85
    Act Density 7.592%

    No Known Activations