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

    Neuronpedia

    INDEX
    Explanations

    past participles or verbs indicating completed actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anja
    -0.17
     Hib
    -0.14
    indow
    -0.14
     segments
    -0.14
     bump
    -0.14
    Statics
    -0.14
    ijke
    -0.14
    amac
    -0.14
     cot
    -0.14
    berger
    -0.13
    POSITIVE LOGITS
     eros
    0.17
    ett
    0.16
    lý
    0.15
     Heal
    0.15
    å¿Ĺ
    0.15
    laughter
    0.14
    iyah
    0.14
    éry
    0.14
    Singleton
    0.14
    alysis
    0.13
    Act Density 0.225%

    No Known Activations