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

    Neuronpedia

    INDEX
    Explanations

    terms related to speeds and data processing

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to data transmission speeds and performances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gey
    -0.65
    Theme
    -0.65
    pb
    -0.65
    nil
    -0.64
     Settlement
    -0.63
    bor
    -0.62
    bour
    -0.62
    Mist
    -0.62
    icans
    -0.62
    displayText
    -0.61
    POSITIVE LOGITS
     speeds
    1.35
     Mach
    1.12
     torque
    1.02
     temperatures
    0.96
     9000
    0.95
     4000
    0.94
     380
    0.94
     550
    0.94
     1050
    0.93
     2500
    0.93
    Act Density 0.233%

    No Known Activations