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

    Neuronpedia

    INDEX
    Explanations

    indicators of personal privacy and confidentiality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Animated
    -0.71
     Hurricanes
    -0.69
    HAM
    -0.66
    liam
    -0.66
    nova
    -0.65
    din
    -0.64
    nia
    -0.64
     Bucket
    -0.64
     Ronaldo
    -0.64
    gain
    -0.63
    POSITIVE LOGITS
     priv
    0.90
     secrets
    0.87
     divul
    0.83
     eaves
    0.82
    itored
    0.81
     confidential
    0.78
    croft
    0.76
    cius
    0.73
    awei
    0.72
    ances
    0.72
    Act Density 0.010%

    No Known Activations