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

    Neuronpedia

    INDEX
    Explanations

    instances of mathematical notation and references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .
    -0.85
    ,
    -0.75
     (
    -0.73
     a
    -0.71
     
    -0.70
     S
    -0.69
    :
    -0.69
    )
    -0.68
     in
    -0.66
     M
    -0.63
    POSITIVE LOGITS
     itſelf
    1.67
     myſelf
    1.56
     Majefty
    1.54
     Reſ
    1.53
     Monfieur
    1.53
     themſelves
    1.51
     himſelf
    1.51
     ſeveral
    1.50
    ſelf
    1.49
     pleaſure
    1.48
    Act Density 0.318%

    No Known Activations