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

    Neuronpedia

    INDEX
    Explanations

    statements expressing opinions or critiques about cartoons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    алÑİ
    -0.15
    allee
    -0.15
    ãĥ
    -0.15
     dementia
    -0.14
     Tobacco
    -0.14
     smoker
    -0.14
     cigarettes
    -0.14
     XM
    -0.14
     tobacco
    -0.14
     Knox
    -0.14
    POSITIVE LOGITS
     She
    0.30
     Princess
    0.26
     Sword
    0.26
     He
    0.25
     MOT
    0.24
     Prince
    0.23
     Ether
    0.23
     Ske
    0.23
     Masters
    0.23
     Castle
    0.23
    Act Density 0.008%

    No Known Activations