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

    Neuronpedia

    INDEX
    Explanations

    phrases related to decision-making and considerations regarding parties or groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Efq
    -0.75
    ſelf
    -0.70
     يتيمه
    -0.68
     whoſe
    -0.67
     and
    -0.65
    ſelves
    -0.63
     myſelf
    -0.62
     Majefty
    -0.61
     ſmall
    -0.60
     however
    -0.59
    POSITIVE LOGITS
     уж
    0.66
     استنادى
    0.64
    ธ์
    0.62
    それに
    0.61
     crossorigin
    0.59
     sogar
    0.58
    hyrchwyd
    0.58
    SuppressLint
    0.57
     dermed
    0.57
     consequently
    0.57
    Act Density 1.249%

    No Known Activations