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

    Neuronpedia

    INDEX
    Explanations

    professional job-related terms and job status updates

    oai_token-act-pair · gpt-3.5-turbo

    references to job positions and employment-related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ioxide
    -0.93
     fragments
    -0.75
     samples
    -0.73
     batches
    -0.73
     images
    -0.73
    rencies
    -0.72
    insk
    -0.71
    amaz
    -0.70
     powd
    -0.70
     typh
    -0.70
    POSITIVE LOGITS
     vacant
    1.04
     vacated
    1.04
     bestowed
    1.01
     conferred
    1.00
     reserved
    0.93
     delegated
    0.91
     occupied
    0.90
     assigned
    0.89
    lain
    0.86
     belonged
    0.84
    Act Density 0.344%

    No Known Activations