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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating discoveries or revelations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     незавершена
    -0.42
     الحره
    -0.41
    epres
    -0.40
     pinulongan
    -0.39
    pea
    -0.39
    Constru
    -0.39
     queſta
    -0.39
    Into
    -0.39
     BoxFit
    -0.38
     beginnetje
    -0.38
    POSITIVE LOGITS
     discovered
    0.79
     scoperto
    0.73
    discovered
    0.72
     discovers
    0.71
     Discovered
    0.67
    httphttps
    0.66
     descobri
    0.65
     Descub
    0.64
     discover
    0.63
     revealed
    0.63
    Act Density 0.291%

    No Known Activations