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

    Neuronpedia

    INDEX
    Explanations

    statements about conditions or states of existence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     mogelijkheden
    -0.83
     exceptions
    -0.79
     caveats
    -0.79
     loopholes
    -0.76
     clichés
    -0.74
     outliers
    -0.73
     metaphors
    -0.73
     approximations
    -0.73
     priorities
    -0.73
     vulnerabilities
    -0.73
    POSITIVE LOGITS
     enfans
    0.87
     stuff
    0.76
     legislation
    0.73
     Stuff
    0.70
    Stuff
    0.68
     cœurs
    0.68
     vérit
    0.68
    stuff
    0.67
     âmes
    0.66
     gouvernements
    0.66
    Act Density 1.272%

    No Known Activations