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

    Neuronpedia

    INDEX
    Explanations

    proper nouns and terms related to specific people, places, and scientific identifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     lavoratori
    -0.45
    *
    -0.44
     AssemblyCompany
    -0.44
    }';
    -0.43
     legality
    -0.43
     endwhile
    -0.42
    Wer
    -0.42
     lieben
    -0.41
    a
    -0.41
    ones
    -0.41
    POSITIVE LOGITS
     purpoſe
    0.94
    ſelves
    0.88
     pleaſure
    0.84
     Efq
    0.81
    ſelf
    0.81
    etheless
    0.79
     reaſon
    0.79
     myſelf
    0.79
     ſur
    0.78
     transfieras
    0.77
    Act Density 2.264%

    No Known Activations