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

    Neuronpedia

    INDEX
    Explanations

    references to strangeness or unusualness in people or things

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Munro
    -0.79
     Pott
    -0.78
     "..\..\..\
    -0.76
     Lott
    -0.76
     casquette
    -0.75
    ↩
    -0.73
     metallo
    -0.72
    ctez
    -0.71
     AssemblyTitle
    -0.71
     parlant
    -0.71
    POSITIVE LOGITS
     Stranger
    0.91
    stranger
    0.90
    Stranger
    0.89
     strangers
    0.69
     stranger
    0.67
     ordini
    0.66
     patrones
    0.66
     Strangers
    0.66
     Lange
    0.64
     Strange
    0.63
    Act Density 0.004%

    No Known Activations