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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing a degree of subtlety or uncertainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     houſe
    -1.25
     pleaſure
    -1.16
     Houſe
    -1.16
     Diſ
    -1.10
     Reſ
    -1.09
     greateſt
    -1.04
     Efq
    -1.03
     purpoſe
    -1.03
     Conſ
    -1.02
     Inſ
    -1.00
    POSITIVE LOGITS
     bit
    1.67
     abit
    1.06
     bits
    1.05
     Bit
    0.98
    bit
    0.98
     BIT
    0.90
    Bit
    0.90
     quite
    0.89
     Bits
    0.88
     unknownFields
    0.81
    Act Density 0.045%

    No Known Activations