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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing uniqueness or distinction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Permanent
    -0.16
    ifu
    -0.16
    UTH
    -0.16
    sst
    -0.16
    inel
    -0.15
    ReturnValue
    -0.15
    chs
    -0.14
    าะ
    -0.14
    stown
    -0.14
    ader
    -0.14
    POSITIVE LOGITS
    ior
    0.15
    marsh
    0.15
    azy
    0.14
    人æīį
    0.14
    uke
    0.14
    anka
    0.14
    alent
    0.14
    aid
    0.14
     friendship
    0.14
    éĿ
    0.14
    Act Density 0.020%

    No Known Activations