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

    Neuronpedia

    INDEX
    Explanations

    notable or important pieces of information

    oai_token-act-pair · gpt-3.5-turbo

    references to "tips" and suggestions related to various situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Asylum
    -0.72
     Recall
    -0.70
    ruciating
    -0.68
     Zed
    -0.67
     Spears
    -0.66
     Palest
    -0.66
     CN
    -0.66
     NAME
    -0.64
     Refugee
    -0.62
     ILCS
    -0.62
    POSITIVE LOGITS
     tip
    1.42
    tip
    1.35
     tips
    1.04
    Tip
    1.00
     tipped
    0.98
    tips
    0.97
     Tip
    0.89
     tipping
    0.87
     jar
    0.84
    idon
    0.82
    Act Density 0.010%

    No Known Activations