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

    Neuronpedia

    INDEX
    Explanations

    symbolic representations and mathematical annotations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ”),
    -0.53
    Архівовано
    -0.51
    "):
    -0.50
    ”—
    -0.48
    πισ
    -0.47
    ),”
    -0.47
    ächtige
    -0.47
    ThroughAttribute
    -0.47
    AutoScale
    -0.46
     Flexib
    -0.46
    POSITIVE LOGITS
     autorytatywna
    0.68
    actéristi
    0.65
    /**
    0.61
    хьтан
    0.60
     发表于
    0.60
     lät
    0.59
    adeloupe
    0.58
     CreateTagHelper
    0.58
    嬸
    0.58
    ppell
    0.57
    Act Density 0.726%

    No Known Activations