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

    Neuronpedia

    INDEX
    Explanations

    phrases or sentences that introduce a particular point or perspective

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating agreement or consensus on key points

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    taboola
    -0.77
    arta
    -0.76
    soever
    -0.71
    pour
    -0.65
    ãĥĩ
    -0.64
    tube
    -0.64
    cot
    -0.64
    earch
    -0.63
    yssey
    -0.63
    industrial
    -0.63
    POSITIVE LOGITS
     one
    1.31
     something
    1.29
     some
    1.22
     another
    1.11
     somet
    1.08
     ONE
    1.03
     two
    1.00
     TWO
    0.94
     several
    0.94
     occasional
    0.94
    Act Density 0.363%

    No Known Activations