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

    Neuronpedia

    INDEX
    Explanations

    phrases related to rates, measurements, and statistical comparisons

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to rates and measurements of various phenomena

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Aires
    -0.84
    roots
    -0.81
    æĦ
    -0.81
    mson
    -0.76
    ingers
    -0.75
    soType
    -0.73
    selves
    -0.72
    smart
    -0.72
    redients
    -0.72
    aces
    -0.71
    POSITIVE LOGITS
     attrition
    1.06
     occurrence
    0.95
     ascent
    0.94
     growth
    0.93
     decline
    0.91
     inflation
    0.91
     escalation
    0.88
     descent
    0.87
     erosion
    0.86
     deterioration
    0.85
    Act Density 0.076%

    No Known Activations