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

    Neuronpedia

    INDEX
    Explanations

    phrases containing numbers followed by a hyphen

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to numerical quantities or measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Rica
    -0.79
     Kafka
    -0.74
     Scotia
    -0.71
     Lovecraft
    -0.70
     Lanka
    -0.70
     Borders
    -0.69
     Richards
    -0.68
     Tort
    -0.67
     Proc
    -0.67
     Nero
    -0.66
    POSITIVE LOGITS
    year
    1.38
    legged
    1.35
    month
    1.27
    dimensional
    1.23
    sided
    1.23
    minute
    1.21
    tailed
    1.20
    fif
    1.20
    headed
    1.17
    thirds
    1.17
    Act Density 0.055%

    No Known Activations