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

    Neuronpedia

    INDEX
    Explanations

    phrases related to voting and awards

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iaz
    -0.15
    aira
    -0.15
     Mits
    -0.15
    ije
    -0.14
     geil
    -0.14
    ender
    -0.13
     Fired
    -0.13
    \Backend
    -0.13
    ota
    -0.13
     spear
    -0.13
    POSITIVE LOGITS
    mgr
    0.16
    дем
    0.16
    eos
    0.16
    DEST
    0.15
    ìĥ
    0.15
    çon
    0.14
     hod
    0.14
    ãĥ¼ãĥ©
    0.14
    루
    0.14
    ynom
    0.14
    Act Density 0.024%

    No Known Activations