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

    Neuronpedia

    INDEX
    Explanations

    phrases related to planning and decision-making

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to teamwork and collaboration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arist
    -0.60
    surprisingly
    -0.60
    *:
    -0.59
     ®
    -0.59
    %:
    -0.55
    NOW
    -0.54
     Alas
    -0.53
     Amid
    -0.52
    ãĤ´ãĥ³
    -0.51
    îĢ
    -0.51
    POSITIVE LOGITS
     [
    0.94
     âĢ¦"
    0.84
    ,'"
    0.82
    ),"
    0.80
    )."
    0.80
     gonna
    0.78
     ..."
    0.78
     everybody
    0.77
    ,"
    0.77
    .'"
    0.75
    Act Density 1.515%

    No Known Activations