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

    Neuronpedia

    INDEX
    Explanations

    equations and mathematical expressions related to changes in differentials and stochastic processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     
    -0.59
     sau
    -0.59
     sa
    -0.58
     ‘
    -0.54
     e
    -0.52
     p
    -0.52
    <eos>
    -0.51
     m
    -0.51
     “
    -0.51
     a
    -0.51
    POSITIVE LOGITS
     pleaſure
    1.14
     cdti
    1.06
    ſelves
    1.03
     Normdatei
    1.03
     فريبيس
    1.02
     itſelf
    1.00
     myſelf
    1.00
     crdi
    1.00
     للمعارف
    0.99
    ſelf
    0.99
    Act Density 0.289%

    No Known Activations