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

    Neuronpedia

    INDEX
    Explanations

    instances of the keyword "new," indicating new object creation or initialization in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ilim
    -0.16
    plier
    -0.16
    baz
    -0.15
     Briggs
    -0.15
     Lam
    -0.14
    iek
    -0.14
     taxpayers
    -0.14
    oplevel
    -0.14
    .inflate
    -0.14
    upp
    -0.13
    POSITIVE LOGITS
     Wasser
    0.17
    agos
    0.15
     ØŃج
    0.14
    wer
    0.14
    ä¸Ī
    0.14
     signalling
    0.14
    cons
    0.14
    ivot
    0.13
    ereo
    0.13
    лаÑĩ
    0.13
    Act Density 0.011%

    No Known Activations