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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "one" or similar phrases suggesting singularity or uniqueness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Dawn
    -0.15
    anges
    -0.15
    inia
    -0.15
    empo
    -0.14
    hic
    -0.14
    оÑĢож
    -0.14
    ilan
    -0.14
    ä¸Ī
    -0.14
    Compiled
    -0.14
    inz
    -0.14
    POSITIVE LOGITS
     day
    0.38
     night
    0.33
     evening
    0.30
     morning
    0.28
     afternoon
    0.28
    ëĤł
    0.25
    æĹ¥
    0.25
     dÃŃa
    0.22
     денÑĮ
    0.22
     ëĤł
    0.21
    Act Density 0.082%

    No Known Activations