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

    Neuronpedia

    INDEX
    Explanations

    references to communication and interaction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     («
    -1.09
     („
    -1.01
     (“
    -0.89
     ("
    -0.89
    (“
    -0.86
     (‘
    -0.82
    ：「
    -0.76
    (‘
    -0.71
    .-"
    -0.71
    ，「
    -0.71
    POSITIVE LOGITS
    期刊论文
    0.52
    Datuak
    0.50
     noastre
    0.49
     tudom
    0.45
    Referring
    0.45
     amelyek
    0.44
    AddTagHelper
    0.43
    Derbyniad
    0.43
     Referring
    0.42
     beginnetje
    0.42
    Act Density 0.191%

    No Known Activations