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

    Neuronpedia

    INDEX
    Explanations

    mentions of usernames and the concept of confidence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Hepburn
    -0.96
     Mehl
    -0.73
     पार
    -0.72
    osoba
    -0.72
     ">=
    -0.70
    ighthouse
    -0.70
     Jameson
    -0.70
     
    -0.69
    hubarb
    -0.67
    ității
    -0.66
    POSITIVE LOGITS
     Merri
    0.88
     Aene
    0.83
     Obre
    0.82
     Trident
    0.81
     Teng
    0.80
     rabbit
    0.79
     Amen
    0.78
     Mauritania
    0.78
     Ultima
    0.77
     Viter
    0.77
    Act Density 0.616%

    No Known Activations