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

    Neuronpedia

    INDEX
    Explanations

    phrases emphasizing the increasing importance and urgency of certain subjects or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    _wr
    -0.15
     Ñħол
    -0.15
    inya
    -0.14
     Datum
    -0.14
    jmu
    -0.14
    §
    -0.14
    lds
    -0.14
    otty
    -0.13
    IRTH
    -0.13
     Axis
    -0.13
    POSITIVE LOGITS
     perhaps
    0.24
     more
    0.20
     now
    0.19
     maybe
    0.18
     than
    0.17
     before
    0.17
     arguably
    0.17
    perhaps
    0.17
     yesterday
    0.17
    than
    0.16
    Act Density 0.035%

    No Known Activations