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

    Neuronpedia

    INDEX
    Explanations

    nouns and specific numerical values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    emek
    -0.16
    verity
    -0.16
    rador
    -0.15
    byname
    -0.15
    plr
    -0.15
    ียม
    -0.15
    urgeon
    -0.15
    /compiler
    -0.15
    WARE
    -0.15
    idity
    -0.15
    POSITIVE LOGITS
     rav
    0.17
     hang
    0.16
    iller
    0.15
    LED
    0.15
     cer
    0.15
    002
    0.15
     Century
    0.14
     Ray
    0.14
    ce
    0.14
     Seg
    0.14
    Act Density 0.010%

    No Known Activations