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

    Neuronpedia

    INDEX
    Explanations

    references to specific scientific studies and data points

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ModelExpression
    -0.93
    GEBURTSDATUM
    -0.90
    SBATCH
    -0.76
    ']=$
    -0.76
     oprot
    -0.75
     floor
    -0.74
    ReusableCell
    -0.74
    iprot
    -0.72
     fewest
    -0.72
    ³/
    -0.71
    POSITIVE LOGITS
    enderror
    0.57
     CURIAM
    0.56
     yoda
    0.50
     répondu
    0.48
    rovnik
    0.46
     Rambo
    0.45
    ,
    0.45
    ukone
    0.44
    fras
    0.43
    antaine
    0.43
    Act Density 0.244%

    No Known Activations