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

    Neuronpedia

    INDEX
    Explanations

    phrases and concepts indicating potential and opportunities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Efq
    -0.71
     houſe
    -0.70
     Jefus
    -0.68
     Chriftian
    -0.67
     thither
    -0.64
    RectangleBorder
    -0.63
     ſtate
    -0.63
     Anm
    -0.61
     themſelves
    -0.61
     sexuelle
    -0.60
    POSITIVE LOGITS
     same
    0.73
    mtd
    0.69
     advantage
    0.67
     enough
    0.62
     necessary
    0.60
    SequentialGroup
    0.59
    avyzd
    0.58
    湃
    0.58
     gevol
    0.57
    OrderService
    0.56
    Act Density 0.190%

    No Known Activations