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

    Neuronpedia

    INDEX
    Explanations

    references to pets and their relationships with humans

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Morav
    -0.17
    Arena
    -0.16
    andon
    -0.16
     Greenwood
    -0.15
    agh
    -0.15
     Pra
    -0.14
    æļ
    -0.14
    inosaur
    -0.14
    orgh
    -0.14
     Siemens
    -0.14
    POSITIVE LOGITS
     Shadow
    0.20
     Buttons
    0.19
     Brut
    0.18
     Spot
    0.18
     Spark
    0.17
    Shadow
    0.17
     Spirit
    0.16
     Beans
    0.16
    Spark
    0.16
    Beans
    0.16
    Act Density 0.162%

    No Known Activations