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

    Neuronpedia

    INDEX
    Explanations

    programming-related syntax and structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    è¦
    -0.16
    velt
    -0.16
    brtc
    -0.15
    orsi
    -0.15
    æ´¥
    -0.14
     Yak
    -0.14
    poÄįet
    -0.14
    λλι
    -0.14
    oppers
    -0.14
     stan
    -0.14
    POSITIVE LOGITS
     Stay
    0.16
    stay
    0.15
    Stay
    0.15
    /goto
    0.14
     stay
    0.14
     staying
    0.14
    icho
    0.14
    åIJ¹
    0.14
    avy
    0.14
    _sensitive
    0.13
    Act Density 0.007%

    No Known Activations