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

    Neuronpedia

    INDEX
    Explanations

    sections where users express gratitude and provide feedback

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aarrggbb
    -0.54
    expandindo
    -0.51
     estekak
    -0.47
    lgari
    -0.46
    RTSN
    -0.44
    adaptiveStyles
    -0.44
     Inflate
    -0.43
     Bailly
    -0.43
    LLocation
    -0.43
    是谁
    -0.42
    POSITIVE LOGITS
    なるほど
    0.68
     effectivement
    0.68
     yes
    0.68
    Actually
    0.68
    Understood
    0.66
     Actually
    0.66
    確かに
    0.63
     fakty
    0.63
     justement
    0.63
     inderdaad
    0.60
    Act Density 0.404%

    No Known Activations