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

    Neuronpedia

    INDEX
    Explanations

    phone numbers

    oai_token-act-pair · gpt-3.5-turbo

    patterns related to phone numbers and contact information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     bang
    -0.71
    culosis
    -0.64
    roups
    -0.60
    uries
    -0.60
    quished
    -0.58
     boarding
    -0.57
    lees
    -0.57
     baskets
    -0.57
     fronts
    -0.56
     arsen
    -0.55
    POSITIVE LOGITS
    776
    0.81
    024
    0.80
    920
    0.80
    200000
    0.78
    800
    0.74
    ĨĴ
    0.73
    thood
    0.73
    237
    0.72
    618
    0.71
    Cola
    0.71
    Act Density 0.159%

    No Known Activations