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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to names and locations, particularly focusing on specific cultural or historical references

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     CreateTagHelper
    -1.15
     feroit
    -0.95
    principalTable
    -0.90
     auroit
    -0.90
     ainfi
    -0.89
    DockStyle
    -0.87
     avoient
    -0.87
    parsedMessage
    -0.82
     rând
    -0.81
     giudi
    -0.81
    POSITIVE LOGITS
     Whit
    0.66
    athione
    0.64
     own
    0.63
    日の
    0.61
     Din
    0.60
    しの
    0.57
     long
    0.57
     die
    0.56
     din
    0.56
    ズの
    0.55
    Act Density 0.008%

    No Known Activations