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

    Neuronpedia

    INDEX
    Explanations

    references to shopping or acquiring items

    oai_token-act-pair · gpt-3.5-turbo

    references to items or gifts intended for others

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ix
    -0.71
    hess
    -0.70
    ieth
    -0.70
    ril
    -0.67
     Begins
    -0.65
    ²
    -0.64
    aan
    -0.61
    edin
    -0.61
     Originally
    -0.61
    ydia
    -0.60
    POSITIVE LOGITS
     sale
    1.16
    bidden
    1.04
    ked
    0.98
    gotten
    0.97
    gettable
    0.97
     example
    0.92
     emergencies
    0.91
     hire
    0.90
    gery
    0.90
    agers
    0.89
    Act Density 0.197%

    No Known Activations