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

    Neuronpedia

    INDEX
    Explanations

    references to the word "scooter" and related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to "scooters"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     chromos
    -0.74
    nant
    -0.70
     cryst
    -0.69
     miscarriage
    -0.67
     mercury
    -0.64
    vironment
    -0.62
    eating
    -0.62
    enc
    -0.62
    intent
    -0.62
     porous
    -0.62
    POSITIVE LOGITS
    ooter
    1.51
    ooters
    1.07
    neys
    0.86
    ragon
    0.83
    hoe
    0.83
    zzi
    0.82
    hod
    0.75
    eers
    0.75
     revolver
    0.75
    Mania
    0.75
    Act Density 0.011%

    No Known Activations