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

    Neuronpedia

    INDEX
    Explanations

    references to lengths or size attributes in a document

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     houſe
    -0.98
     itſelf
    -0.96
    othesis
    -0.93
     Theſe
    -0.90
     preſent
    -0.89
     Houſe
    -0.86
     uſe
    -0.84
    ⁎
    -0.84
     Fenton
    -0.83
     becauſe
    -0.82
    POSITIVE LOGITS
     Len
    1.11
     len
    1.09
    len
    1.09
    Len
    1.04
     Lenny
    0.81
     LEN
    0.80
     Leonard
    0.80
    Lena
    0.79
     SqlCommand
    0.77
     lenker
    0.73
    Act Density 0.006%

    No Known Activations