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

    Neuronpedia

    INDEX
    Explanations

    instances of contrast or contradiction in statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     mxArray
    -0.41
     micro
    -0.39
     multi
    -0.39
    ✷
    -0.38
     radi
    -0.35
     enables
    -0.33
    XmlAccessType
    -0.33
     ray
    -0.33
     poste
    -0.32
     gravity
    -0.32
    POSITIVE LOGITS
     defaultstate
    0.73
     CreateTagHelper
    0.69
    中でも
    0.53
    BagLayout
    0.51
    AndroidJUnit
    0.50
    mbggenerated
    0.50
    chieht
    0.49
    SequentialGroup
    0.48
    XmlAccessorType
    0.47
     Inſ
    0.47
    Act Density 0.390%

    No Known Activations