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

    Neuronpedia

    INDEX
    Explanations

    instances where something is described as steady

    oai_token-act-pair · gpt-3.5-turbo

    phrases that convey consistency or reliability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    FactoryReloaded
    -0.79
    çīĪ
    -0.76
    VL
    -0.69
    aucus
    -0.67
    dor
    -0.66
    dylib
    -0.66
    asper
    -0.65
     Rou
    -0.65
     Libraries
    -0.65
    odes
    -0.64
    POSITIVE LOGITS
     steady
    0.99
    motion
    0.92
     pace
    0.86
     stream
    0.82
     drip
    0.81
    weights
    0.80
     flow
    0.79
     progression
    0.76
     intervals
    0.75
     slope
    0.74
    Act Density 0.015%

    No Known Activations