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

    Neuronpedia

    INDEX
    Explanations

    patterns of numerical data or references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ]='\
    -1.30
     للمعارف
    -1.25
     autorytatywna
    -1.23
    Autoritní
    -1.22
    '],
    -1.22
    ']],
    -1.20
    ,:);
    -1.18
     }}"></
    -1.16
    دانشنامهٔ
    -1.15
    }")
    -1.15
    POSITIVE LOGITS
    2
    3.47
    3
    2.12
    1
    2.06
    4
    1.95
    5
    1.84
    6
    1.78
    7
    1.70
    8
    1.67
    0
    1.63
    9
    1.58
    Act Density 1.611%

    No Known Activations