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

    Neuronpedia

    INDEX
    Explanations

    words related to representation and correspondence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     OkHttpClient
    -0.86
    ueger
    -0.78
    chaikovsky
    -0.75
     Normdatei
    -0.74
    XtraEditors
    -0.73
    issues
    -0.69
    воро
    -0.66
    issue
    -0.66
     disqual
    -0.66
     Mui
    -0.65
    POSITIVE LOGITS
     representation
    1.99
     representations
    1.93
    Represent
    1.91
     representing
    1.91
     REPRESENT
    1.90
     represent
    1.88
     Representations
    1.87
     Represent
    1.87
     Representation
    1.86
     represents
    1.83
    Act Density 0.113%

    No Known Activations