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

    Neuronpedia

    INDEX
    Explanations

    numerical values related to time or measurements

    oai_token-act-pair · gpt-3.5-turbo

    numerical values or statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wart
    -0.87
    scape
    -0.83
    fare
    -0.78
    ways
    -0.77
    sterdam
    -0.77
    apolis
    -0.77
    oha
    -0.76
    usky
    -0.76
    algia
    -0.76
    nam
    -0.76
    POSITIVE LOGITS
     lbs
    0.77
     MHz
    0.75
     pounds
    0.75
    PDATE
    0.73
    MENTS
    0.71
    lbs
    0.70
    MHz
    0.69
    MENT
    0.65
     calories
    0.65
    acebook
    0.64
    Act Density 0.060%

    No Known Activations