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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating novelty or uniqueness in research findings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /interface
    -0.17
    ssel
    -0.17
    achine
    -0.15
    ReadStream
    -0.15
    èĨ
    -0.14
     Kurd
    -0.13
    çĽijåIJ¬é¡µéĿ¢
    -0.13
    IODevice
    -0.13
     showc
    -0.13
     viz
    -0.13
    POSITIVE LOGITS
    avra
    0.16
    ektor
    0.16
    ityEngine
    0.15
    atitude
    0.15
    alink
    0.15
    ventus
    0.14
    .Embed
    0.14
    figcaption
    0.14
    æĢ§çļĦ
    0.14
    ofday
    0.14
    Act Density 0.342%

    No Known Activations