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

    Neuronpedia

    INDEX
    Explanations

    references to cooking techniques and ingredients

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    _LOOP
    -0.16
     cigaret
    -0.16
     eskort
    -0.14
    oje
    -0.14
     okol
    -0.14
    Loop
    -0.14
    inden
    -0.13
     discounts
    -0.13
    undi
    -0.13
    _MATRIX
    -0.13
    POSITIVE LOGITS
     measurement
    0.24
    Measurement
    0.23
     Measurement
    0.23
     measurements
    0.22
    measurement
    0.22
     Measurements
    0.21
     measuring
    0.20
    measure
    0.19
    Measure
    0.19
     Instructions
    0.19
    Act Density 0.190%

    No Known Activations