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

    Neuronpedia

    INDEX
    Explanations

    keywords related to tracking or monitoring activities and technology

    oai_token-act-pair · gpt-3.5-turbo

    terms related to tracking and surveillance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ahu
    -0.75
    annis
    -0.69
    osi
    -0.68
    vette
    -0.67
    acco
    -0.65
    urt
    -0.64
     substit
    -0.64
    forth
    -0.63
    anti
    -0.61
    perty
    -0.61
    POSITIVE LOGITS
    itored
    0.85
     Tracks
    0.85
    illance
    0.80
    gered
    0.79
    gers
    0.77
    suit
    0.76
    suits
    0.76
     tracks
    0.75
     bracelet
    0.74
    masters
    0.72
    Act Density 0.028%

    No Known Activations