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

    Neuronpedia

    INDEX
    Explanations

    verbs related to the ability to do something

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the ability or capacity to perform actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    soDeliveryDate
    -0.83
    cloth
    -0.81
    ested
    -0.77
    listed
    -0.75
    backer
    -0.75
    esting
    -0.72
    bats
    -0.70
    tops
    -0.66
    cluded
    -0.66
     Weston
    -0.66
    POSITIVE LOGITS
     manipulate
    1.34
     communicate
    1.31
     withstand
    1.29
     generate
    1.21
     mobilize
    1.20
     predict
    1.18
     innovate
    1.14
     navigate
    1.13
     differentiate
    1.13
     distinguish
    1.13
    Act Density 0.116%

    No Known Activations