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

    Neuronpedia

    INDEX
    Explanations

    specific actions or decisions that individuals declare they will take in the future

    oai_token-act-pair · gpt-3.5-turbo

    the word "would" and its variants

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    76561
    -0.63
    quickShipAvailable
    -0.62
     Computing
    -0.59
    IDENT
    -0.59
    Dex
    -0.58
    Sounds
    -0.58
    ohyd
    -0.57
    claimed
    -0.56
    RD
    -0.56
    Creat
    -0.56
    POSITIVE LOGITS
     seek
    1.11
     investigate
    1.06
     cooperate
    1.06
     prefer
    1.05
     gladly
    1.05
     pursue
    1.03
     continue
    1.03
     refrain
    1.02
     intensify
    1.00
     withhold
    1.00
    Act Density 0.143%

    No Known Activations