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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the action of giving something to someone

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "to" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ndra
    -0.71
    neapolis
    -0.70
     adolesc
    -0.67
    clud
    -0.66
    apeake
    -0.66
    autical
    -0.64
     oun
    -0.63
     resil
    -0.63
     billed
    -0.63
    soDeliveryDate
    -0.62
    POSITIVE LOGITS
     acquire
    0.78
     compensate
    0.78
     accompany
    0.76
     regain
    0.74
     appease
    0.74
     whoever
    0.71
     cultivate
    0.71
     commemorate
    0.70
     maximize
    0.69
    amen
    0.69
    Act Density 0.128%

    No Known Activations