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

    Neuronpedia

    INDEX
    Explanations

    occurrences of specific sound patterns or phonetic elements in words

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.04
    1:0.02
    2:0.03
    3:0.05
    4:0.03
    5:0.03
    6:0.13
    7:0.02
    8:0.03
    9:0.51
    10:0.02
    11:0.03
    Negative Logits
     Willis
    -5.07
     Wynne
    -3.67
     Polk
    -3.49
     Von
    -3.34
     Jenna
    -3.29
     neutron
    -3.26
     Thermal
    -3.26
     Corn
    -3.25
     Mel
    -3.23
     Ther
    -3.22
    POSITIVE LOGITS
    ag
    6.49
    ags
    6.35
    AG
    6.01
    og
    5.83
    OG
    5.42
    agg
    5.38
    IG
    5.34
     Og
    5.32
    ig
    5.22
    agging
    5.21
    Act Density 0.181%

    No Known Activations