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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a function or usefulness of an object or action

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating functionality or purpose

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     inspected
    -0.68
    gins
    -0.59
    opher
    -0.58
    uesday
    -0.58
     Obj
    -0.58
    acqu
    -0.57
    ti
    -0.57
    pex
    -0.57
    ibliography
    -0.56
    ipl
    -0.54
    POSITIVE LOGITS
     purpose
    0.72
    umes
    0.69
     primarily
    0.69
     mainly
    0.68
    icer
    0.68
     as
    0.68
     purposes
    0.67
    ibaba
    0.66
     interests
    0.66
    agonists
    0.66
    Act Density 0.032%

    No Known Activations