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

    Neuronpedia

    INDEX
    Explanations

    references to academic qualifications and research roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    RemoveField
    -0.65
    ROLS
    -0.59
     paradis
    -0.58
    Ян
    -0.58
     organisers
    -0.56
    ffindor
    -0.56
    awtextra
    -0.55
    //</
    -0.54
     kasarigan
    -0.54
    ism
    -0.53
    POSITIVE LOGITS
     thesis
    1.09
    doctoral
    1.07
     dissertation
    1.07
    SBATCH
    1.00
     doctoral
    1.00
    Thesis
    0.96
    thesis
    0.96
     Dissertation
    0.93
    Doctoral
    0.92
     THESIS
    0.92
    Act Density 0.166%

    No Known Activations