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

    Neuronpedia

    INDEX
    Explanations

    references to paternal figures or fathers in text

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Negative Logits
     OnEnable
    -0.55
     ModelExpression
    -0.52
    Leif
    -0.51
    simplex
    -0.50
     handcuffs
    -0.50
    Források
    -0.49
    abestanden
    -0.48
    stdc
    -0.47
    expandindo
    -0.47
     varn
    -0.47
    POSITIVE LOGITS
    BagConstraints
    0.86
    quiao
    0.81
     kasarigan
    0.75
     disparu
    0.74
    Namaste
    0.74
     Myanmar
    0.73
    zet
    0.72
     >=",
    0.72
    bourne
    0.71
    resizingMask
    0.69
    Act Density 0.101%

    No Known Activations