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

    Neuronpedia

    INDEX
    Explanations

    numerical data points and their interpretations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     estekak
    -0.87
     chi̍t
    -0.87
    DrawerToggle
    -0.86
    findpost
    -0.85
    \{\\
    -0.84
    picasso
    -0.83
     ddelweddau
    -0.82
     Мексичка
    -0.81
    multicolumn
    -0.79
    ünst
    -0.78
    POSITIVE LOGITS
     Coates
    0.59
    Beat
    0.52
    ted
    0.52
     initializes
    0.52
    ről
    0.51
     zato
    0.50
     Cina
    0.50
     angele
    0.49
     Botany
    0.49
    ing
    0.49
    Act Density 0.558%

    No Known Activations