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

    Neuronpedia

    INDEX
    Explanations

    uncommon percentages or numerical values

    oai_token-act-pair · gpt-3.5-turbo

    percentages and numeric values related to rarity or frequency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pecially
    -0.77
    rament
    -0.73
     showc
    -0.71
     thous
    -0.70
     lett
    -0.69
    ãĤ©
    -0.68
     compr
    -0.68
    âĢ¢âĢ¢âĢ¢âĢ¢
    -0.68
     therap
    -0.67
     grain
    -0.66
    POSITIVE LOGITS
     ABV
    0.73
     Decay
    0.73
     Hig
    0.68
    steamapps
    0.68
    ecided
    0.67
     NTS
    0.67
     Deadline
    0.66
    -+
    0.65
     TBA
    0.65
     opacity
    0.64
    Act Density 0.035%

    No Known Activations