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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to scientific and medical terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    PreferredItem
    -0.84
     Kell
    -0.67
     Viel
    -0.66
     ide
    -0.65
     Balboa
    -0.65
     Lark
    -0.64
     Stimm
    -0.64
     Ide
    -0.63
     Kem
    -0.63
    part
    -0.63
    POSITIVE LOGITS
     Wittenberg
    0.85
    silian
    0.76
     Jind
    0.73
     Insulation
    0.72
     Hohen
    0.70
    })));
    0.70
     Jarrett
    0.69
    بوابة
    0.69
    Morgen
    0.68
    })()
    0.68
    Act Density 2.859%

    No Known Activations