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

    Neuronpedia

    INDEX
    Explanations

    references to fantastical creatures and elements of horror

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ovit
    -0.17
    оÑĢов
    -0.16
    rabbit
    -0.16
    çĽĹ
    -0.15
     rabbit
    -0.15
    buz
    -0.15
    侯
    -0.14
     hust
    -0.14
     Dynamics
    -0.14
    ocator
    -0.14
    POSITIVE LOGITS
     Godzilla
    0.35
     Kai
    0.28
     monsters
    0.25
     Kong
    0.24
    God
    0.24
     Pacific
    0.24
     Monsters
    0.23
     Monster
    0.23
     atomic
    0.23
     monster
    0.23
    Act Density 0.012%

    No Known Activations