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

    Neuronpedia

    INDEX
    Explanations

    dates and temporal references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Theſe
    -1.26
     Majefty
    -1.23
    ſelf
    -1.23
    ſelves
    -1.19
     Perſ
    -1.14
     Diſ
    -1.14
     Efq
    -1.10
     houſe
    -1.08
     Inſ
    -1.08
     Reſ
    -1.07
    POSITIVE LOGITS
     when
    0.66
    .
    0.63
    ,
    0.61
     during
    0.55
    when
    0.54
     
    0.49
     (
    0.48
     годах
    0.48
     poète
    0.48
    l
    0.47
    Act Density 0.431%

    No Known Activations