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

    Neuronpedia

    INDEX
    Explanations

    percentages and numerical figures

    oai_token-act-pair · gpt-3.5-turbo

    numerical data related to financial percentages and changes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     alienation
    -0.62
     narciss
    -0.62
     Converted
    -0.61
    ivia
    -0.59
     insecurity
    -0.58
     forgiven
    -0.56
     vanity
    -0.56
     dissatisfaction
    -0.55
     recourse
    -0.55
     Situation
    -0.54
    POSITIVE LOGITS
    uously
    1.13
    mins
    0.93
    aciously
    0.93
    bp
    0.92
    th
    0.91
     times
    0.88
    ½
    0.83
    ft
    0.81
    pt
    0.81
    lbs
    0.81
    Act Density 0.133%

    No Known Activations