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

    Neuronpedia

    INDEX
    Explanations

    concepts related to social and systemic challenges

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    akra
    -0.15
    ikut
    -0.15
    pheres
    -0.15
    entes
    -0.14
    ยว
    -0.14
    akk
    -0.14
    ÑģÑĥÑĤ
    -0.14
    опаÑģ
    -0.14
    IGINAL
    -0.13
    uno
    -0.13
    POSITIVE LOGITS
     bright
    0.65
     silver
    0.64
    bright
    0.55
     brighter
    0.52
     Silver
    0.52
    silver
    0.51
     Bright
    0.48
    Silver
    0.47
    Bright
    0.47
     brightness
    0.40
    Act Density 0.148%

    No Known Activations