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

    Neuronpedia

    INDEX
    Explanations

    references to horror and Lovecraftian themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    天天
    -0.15
    鹿
    -0.15
    oux
    -0.14
    724
    -0.14
     Tir
    -0.14
     scout
    -0.14
     Guth
    -0.14
     Hera
    -0.14
     McCartney
    -0.13
     Paladin
    -0.13
    POSITIVE LOGITS
     Love
    0.36
    Love
    0.32
     Lover
    0.24
     Yog
    0.24
     Nec
    0.23
     HP
    0.23
     LOVE
    0.22
     tent
    0.22
     Elder
    0.22
     love
    0.21
    Act Density 0.020%

    No Known Activations