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

    Neuronpedia

    INDEX
    Explanations

    references to project objectives or aims

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Majefty
    -1.04
     cdti
    -0.97
     purpoſe
    -0.97
     pleaſure
    -0.96
     houſe
    -0.93
     Houſe
    -0.86
     ſeveral
    -0.84
     cauſe
    -0.84
     Diſ
    -0.84
     leaſt
    -0.83
    POSITIVE LOGITS
     A
    0.58
     Q
    0.51
    первых
    0.50
     Re
    0.50
     newBuilder
    0.49
     E
    0.49
     W
    0.47
    ul
    0.47
    li
    0.47
     X
    0.47
    Act Density 0.382%

    No Known Activations