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

    Neuronpedia

    INDEX
    Explanations

    indications of theft and theft-related activities

    oai_token-act-pair · gpt-3.5-turbo

    references to theft and related criminal activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enegger
    -0.72
    ombs
    -0.72
    shr
    -0.72
    present
    -0.70
    travel
    -0.69
    ennett
    -0.68
    phas
    -0.67
    IX
    -0.66
    nant
    -0.66
    aeda
    -0.65
    POSITIVE LOGITS
     spree
    0.98
     Theft
    0.96
     theft
    0.86
     thefts
    0.81
     thief
    0.80
     unfocusedRange
    0.80
     thieves
    0.76
     stealing
    0.74
     robbery
    0.72
     stalk
    0.70
    Act Density 0.013%

    No Known Activations