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

    Neuronpedia

    INDEX
    Explanations

    codes or technical terms related to programming or technology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .
    -0.71
    <eos>
    -0.70
     
    -0.69
     $
    -0.67
     स्
    -0.66
     con
    -0.66
     "
    -0.64
     شدم
    -0.63
    2
    -0.62
     شدند
    -0.62
    POSITIVE LOGITS
     itſelf
    1.56
     myſelf
    1.51
     Efq
    1.38
     iſt
    1.24
     Theſe
    1.24
     becauſe
    1.20
     uſed
    1.19
     Jefus
    1.18
     themſelves
    1.16
     raiſ
    1.13
    Act Density 0.251%

    No Known Activations