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

    Neuronpedia

    INDEX
    Explanations

    keywords related to technology and devices, particularly those including the word "Ultra"

    oai_token-act-pair · gpt-3.5-turbo

    instances of "Ultra" followed by numeric values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    */(
    -0.92
     Cosponsors
    -0.71
     Learns
    -0.70
    cific
    -0.70
    ophers
    -0.69
    ãģ®éŃĶ
    -0.67
    Ĺ
    -0.66
    ī
    -0.66
    ij
    -0.65
    tons
    -0.64
    POSITIVE LOGITS
    raviolet
    0.94
    Ultra
    0.89
    visor
    0.83
    avorite
    0.82
     Ultra
    0.79
    iolet
    0.77
    orthodox
    0.75
     violet
    0.71
    nova
    0.69
    uesday
    0.68
    Act Density 0.005%

    No Known Activations