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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal and governmental matters

    oai_token-act-pair · gpt-3.5-turbo

    instances of punctuation, specifically commas and percentages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iple
    -0.65
    uber
    -0.60
    ocl
    -0.58
    ¬¼
    -0.56
    yon
    -0.51
    endo
    -0.51
    asma
    -0.51
    chin
    -0.51
    ub
    -0.50
    ver
    -0.49
    POSITIVE LOGITS
     namely
    1.06
     albeit
    1.04
     although
    0.97
     whereas
    0.94
     including
    0.90
     which
    0.89
     though
    0.83
     wherein
    0.83
     culminating
    0.82
     but
    0.82
    Act Density 0.659%

    No Known Activations