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

    Neuronpedia

    INDEX
    Explanations

    terms related to duplication and significant numbers or statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yster
    -0.18
    zie
    -0.18
    anse
    -0.16
    usalem
    -0.15
    oise
    -0.15
    serie
    -0.15
    .opend
    -0.15
    Seats
    -0.14
    otto
    -0.14
    abis
    -0.14
    POSITIVE LOGITS
    RIPT
    0.16
    igin
    0.15
     Douglas
    0.15
    _dual
    0.15
     loc
    0.15
    eway
    0.15
    iais
    0.15
    IA
    0.15
    loc
    0.14
     pace
    0.14
    Act Density 0.005%

    No Known Activations