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

    Neuronpedia

    INDEX
    Explanations

    commands or instructions given in a specific format

    oai_token-act-pair · gpt-3.5-turbo

    conditional phrases indicating user actions or requirements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    âĢİ
    -0.84
    GREEN
    -0.75
    ãĤ¤ãĥĪ
    -0.74
    wikipedia
    -0.73
     Sco
    -0.70
    Cu
    -0.70
    Tomorrow
    -0.69
    Pinterest
    -0.69
    Ú
    -0.69
    Mad
    -0.68
    POSITIVE LOGITS
     unsure
    0.85
     discrepancy
    0.81
     configured
    0.81
     purchased
    0.78
     duplicate
    0.74
     breach
    0.72
     subclass
    0.72
     incorrectly
    0.71
     requested
    0.70
     exceed
    0.70
    Act Density 0.270%

    No Known Activations