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

    Neuronpedia

    INDEX
    Explanations

    phrases related to unusual experiences or oddities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     swamp
    -0.15
    lier
    -0.15
    desk
    -0.15
     há»ĵ
    -0.15
     lake
    -0.14
    ischer
    -0.14
     Gecko
    -0.14
     Lake
    -0.14
    estro
    -0.14
     desert
    -0.14
    POSITIVE LOGITS
     Oregon
    0.27
     Tato
    0.24
     tide
    0.23
    Oregon
    0.23
     Pacific
    0.22
     Till
    0.21
    Pacific
    0.21
     surf
    0.20
     seals
    0.19
     Oswald
    0.19
    Act Density 0.028%

    No Known Activations