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

    Neuronpedia

    INDEX
    Explanations

    terms and concepts related to theoretical frameworks and models for understanding implementation strategies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    penup
    -0.47
    графія
    -0.47
     reconstructions
    -0.47
    erialized
    -0.46
     ambiguous
    -0.45
     thiệu
    -0.44
    INTERFACE
    -0.43
     raconter
    -0.43
     مشتر
    -0.43
     indiquer
    -0.43
    POSITIVE LOGITS
    AxisAlignment
    0.70
    AndEndTag
    0.61
    BagConstraints
    0.60
    kheim
    0.60
    bootstrapcdn
    0.60
     Wiktionnaire
    0.58
     Tinto
    0.58
    SPJ
    0.57
     lobe
    0.57
     theory
    0.56
    Act Density 0.578%

    No Known Activations