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

    Neuronpedia

    INDEX
    Explanations

    terms and phrases associated with programming and technical jargon in various languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     WTF
    -0.14
    ierre
    -0.14
     KD
    -0.14
     Kavanaugh
    -0.14
     RV
    -0.13
    åīij
    -0.13
     ‘
    -0.13
    obuf
    -0.13
    aniel
    -0.13
     VP
    -0.13
    POSITIVE LOGITS
     Frank
    0.32
     Frankie
    0.28
    Frank
    0.27
     Morris
    0.24
     Jewish
    0.22
     Leo
    0.22
     frank
    0.22
     Jews
    0.21
     factory
    0.20
    Mor
    0.20
    Act Density 0.002%

    No Known Activations