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

    Neuronpedia

    INDEX
    Explanations

    expressions related to levels and complexity settings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zano
    -0.16
    angs
    -0.14
     vehicle
    -0.14
    alez
    -0.14
     Guest
    -0.14
    ogui
    -0.14
    ipple
    -0.14
    onas
    -0.13
     Emin
    -0.13
     guest
    -0.13
    POSITIVE LOGITS
    rica
    0.16
    aren
    0.15
    kon
    0.14
    ystone
    0.14
    marker
    0.14
    rone
    0.14
     Vampire
    0.14
    766
    0.14
    ana
    0.14
    ington
    0.13
    Act Density 0.018%

    No Known Activations