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

    Neuronpedia

    INDEX
    Explanations

    phrases related to theft or stealing

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "steal" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ichick
    -0.79
    hedon
    -0.75
    ŀ
    -0.74
    SPA
    -0.73
    present
    -0.72
     Unsure
    -0.71
    foreseen
    -0.69
    rition
    -0.69
    olver
    -0.69
    etheless
    -0.68
    POSITIVE LOGITS
     glances
    1.00
     goods
    0.85
     from
    0.85
     credit
    0.84
     funds
    0.82
     away
    0.82
     stolen
    0.82
     valuable
    0.80
     money
    0.76
     priceless
    0.74
    Act Density 0.075%

    No Known Activations