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

    Neuronpedia

    INDEX
    Explanations

    propositions and conjunctions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to challenges and teamwork in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    *:
    -0.56
    antic
    -0.55
     Amid
    -0.55
    ãĤ´ãĥ³
    -0.55
     Alas
    -0.51
    arist
    -0.50
     Occ
    -0.48
     Bare
    -0.48
     ®
    -0.48
    èĢħ
    -0.47
    POSITIVE LOGITS
     [
    0.80
    entimes
    0.78
     mathemat
    0.78
     ..."
    0.74
     gonna
    0.73
    )."
    0.72
    ,'"
    0.71
     âĢ¦"
    0.70
    ),"
    0.70
     incent
    0.68
    Act Density 1.617%

    No Known Activations