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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "sur" in various contexts, possibly related to surrogacy or support roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Niko
    -0.77
    ✨:
    -0.75
    Niko
    -0.73
    ACKS
    -0.66
     جغرافيا
    -0.65
     Monde
    -0.65
     Beckman
    -0.65
     Fleck
    -0.64
     Kazan
    -0.64
    杖
    -0.63
    POSITIVE LOGITS
     SUR
    2.00
    Sur
    1.99
    sur
    1.97
     Sur
    1.88
    SUR
    1.86
     sur
    1.79
     Surya
    1.29
     surcharge
    1.26
     surfer
    1.25
     surfers
    1.22
    Act Density 0.102%

    No Known Activations