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

    Neuronpedia

    INDEX
    Explanations

    names of scholars and their affiliations in academic discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    MigrationBuilder
    -1.04
    GEBURTSDATUM
    -0.95
     oprot
    -0.93
    SBATCH
    -0.93
    ReusableCell
    -0.91
    Geplaatst
    -0.88
     חיצוניים
    -0.87
     myſelf
    -0.86
     pleaſure
    -0.86
    Clik
    -0.85
    POSITIVE LOGITS
    ,
    0.45
    wtf
    0.38
    .
    0.38
    enn
    0.36
     argues
    0.36
    <eos>
    0.36
    ː
    0.36
     parques
    0.35
     Brown
    0.34
    ghouse
    0.34
    Act Density 0.562%

    No Known Activations