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

    Neuronpedia

    INDEX
    Explanations

    numbers related to politics and percentages

    oai_token-act-pair · gpt-3.5-turbo

    references to the number 47

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Collider
    -0.69
    agine
    -0.65
    achus
    -0.64
     actu
    -0.64
    urus
    -0.61
     simul
    -0.60
    vern
    -0.60
     parity
    -0.59
     cooker
    -0.58
    ogical
    -0.57
    POSITIVE LOGITS
    00
    1.00
    rpm
    0.90
    MJ
    0.86
     msec
    0.86
    oslov
    0.80
    inosaur
    0.79
    istani
    0.79
    rd
    0.79
    åŃIJ
    0.71
    MU
    0.69
    Act Density 0.049%

    No Known Activations