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

    Neuronpedia

    INDEX
    Explanations

    elements related to religious or spiritual observances and practices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     queſta
    -1.53
    <unused79>
    -1.46
    <unused8>
    -1.46
    [@BOS@]
    -1.45
    <unused47>
    -1.45
    <unused23>
    -1.45
    <unused41>
    -1.45
    <unused28>
    -1.45
    <unused14>
    -1.45
    <unused16>
    -1.45
    POSITIVE LOGITS
     „
    0.63
     na
    0.63
     pod
    0.61
     z
    0.61
     od
    0.59
     po
    0.57
     roz
    0.56
     do
    0.54
     u
    0.52
     o
    0.51
    Act Density 0.028%

    No Known Activations