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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a binary decision or a choice between two possibilities

    oai_token-act-pair · gpt-3.5-turbo

    conditional phrases indicating uncertainty or indecision

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    çīĪ
    -0.71
    ĸļ
    -0.69
     Rooms
    -0.67
    ãĤ¼ãĤ¦ãĤ¹
    -0.66
    äºĶ
    -0.66
    083
    -0.65
    ¿
    -0.65
    ãĥķãĤ©
    -0.65
    SourceFile
    -0.65
     srfAttach
    -0.62
    POSITIVE LOGITS
     technically
    0.84
     existed
    0.81
     swayed
    0.77
     qualifies
    0.77
    theless
    0.76
     mete
    0.72
     necessarily
    0.71
     they
    0.71
     qualified
    0.69
    igham
    0.68
    Act Density 0.018%

    No Known Activations