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

    Neuronpedia

    INDEX
    Explanations

    expressions of thoughts, beliefs, and uncertainties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yük
    -0.07
    ï¼ļ↵↵
    -0.07
    aar
    -0.07
    fak
    -0.06
     ------------------------------------------------------------------------↵
    -0.06
     ìŀĪëĭ¤ê³ł
    -0.06
    uk
    -0.06
     Replies
    -0.06
    çĽĬ
    -0.06
    adel
    -0.06
    POSITIVE LOGITS
    iversit
    0.08
     Pend
    0.07
    ãĤ·ãĤ¢
    0.07
    _mB
    0.07
    SetBranch
    0.07
     MB
    0.07
    ollipop
    0.06
    -Sah
    0.06
    ALSE
    0.06
    olars
    0.06
    Act Density 0.040%

    No Known Activations