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

    Neuronpedia

    INDEX
    Explanations

    entities and terms related to regulations and commerce

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.02
    2:0.06
    3:0.14
    4:0.36
    5:0.03
    6:0.04
    7:0.07
    8:0.03
    9:0.05
    10:0.08
    11:0.06
    Negative Logits
    iesta
    -1.58
    uces
    -1.48
    ravity
    -1.47
    uten
    -1.46
    ilar
    -1.46
    lp
    -1.45
    iban
    -1.44
    icio
    -1.43
    inness
    -1.41
    xp
    -1.41
    POSITIVE LOGITS
     contexts
    1.68
     occupations
    1.65
     purposes
    1.61
     situations
    1.61
    ▬
    1.59
     situation
    1.52
     coasts
    1.49
     provinces
    1.48
     locations
    1.46
     regions
    1.45
    Act Density 0.026%

    No Known Activations