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

    Neuronpedia

    INDEX
    Explanations

    words that indicate personal relationships and social interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ExecuteAsync
    -1.08
    SourceChecksum
    -1.02
    TagMode
    -1.00
    UnusedPrivate
    -1.00
     itſelf
    -0.97
    TypedDataSet
    -0.95
    SpringBootTest
    -0.93
     pleaſure
    -0.92
    httphttps
    -0.92
     Савезне
    -0.91
    POSITIVE LOGITS
     in
    0.85
     as
    0.74
     on
    0.71
     from
    0.69
     with
    0.68
     to
    0.66
     for
    0.66
     him
    0.64
     sendiri
    0.61
     her
    0.61
    Act Density 0.291%

    No Known Activations