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

    Neuronpedia

    INDEX
    Explanations

    phrases related to politics and economy

    oai_token-act-pair · gpt-3.5-turbo

    instances of punctuation, particularly commas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iple
    -0.69
    ocl
    -0.67
    rio
    -0.62
    irie
    -0.61
    ¬¼
    -0.61
    chin
    -0.58
    rup
    -0.58
    vered
    -0.57
    eport
    -0.56
    itol
    -0.56
    POSITIVE LOGITS
     albeit
    1.19
     namely
    1.05
     whereas
    1.04
     although
    1.01
     which
    0.99
     including
    0.93
     culminating
    0.90
     but
    0.87
     implying
    0.87
     whereby
    0.86
    Act Density 0.697%

    No Known Activations