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

    Neuronpedia

    INDEX
    Explanations

    phrases related to initiating or planning future actions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "set" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    issance
    -1.03
    æѦ
    -0.67
    inventoryQuantity
    -0.64
     Taste
    -0.63
    lux
    -0.63
    asive
    -0.62
    vine
    -0.62
    ilee
    -0.60
    luence
    -0.60
    UGE
    -0.58
    POSITIVE LOGITS
    tle
    0.93
    tering
    0.91
     abl
    0.90
    offs
    0.85
     forth
    0.83
    list
    0.82
    tered
    0.82
    ters
    0.79
    ter
    0.78
    itia
    0.75
    Act Density 0.033%

    No Known Activations