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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate examples or references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Portail
    -0.71
    anstalt
    -0.66
    Portail
    -0.62
    ***/
    -0.61
    terness
    -0.60
    hant
    -0.59
    Datuak
    -0.59
    StoryboardSegue
    -0.56
    IFUL
    -0.56
    ExtendWith
    -0.55
    POSITIVE LOGITS
     as
    0.79
     shown
    0.73
     تضيفلها
    0.68
     well
    0.66
     soos
    0.65
    shown
    0.62
     indicated
    0.60
    as
    0.57
    ņas
    0.57
     opposed
    0.56
    Act Density 0.256%

    No Known Activations