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

    Neuronpedia

    INDEX
    Explanations

    adjectives and nouns related to attributes or characteristics

    oai_token-act-pair · gpt-3.5-turbo

    descriptive phrases related to lifestyle and social behaviors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    RESULTS
    -0.47
    versely
    -0.47
    CHAT
    -0.41
     McDonnell
    -0.40
     yourselves
    -0.39
    DATA
    -0.39
     Fiscal
    -0.39
    yss
    -0.38
     tentative
    -0.38
     QUEST
    -0.37
    POSITIVE LOGITS
    smanship
    0.69
    eers
    0.61
    ebted
    0.51
    Initialized
    0.50
    ploma
    0.49
    eering
    0.49
    edly
    0.47
    igraph
    0.47
     affair
    0.47
    ãĤ´ãĥ³
    0.46
    Act Density 3.752%

    No Known Activations