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

    Neuronpedia

    INDEX
    Explanations

    expressions of uncertainty or hesitation in conversation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     للاسماء
    -1.13
    <unused52>
    -0.98
    <unused28>
    -0.98
    <unused68>
    -0.97
    [@BOS@]
    -0.97
    <unused74>
    -0.97
    <unused14>
    -0.97
    <unused8>
    -0.97
    <pad>
    -0.96
    <unused3>
    -0.96
    POSITIVE LOGITS
    <bos>
    0.46
     (
    0.37
     @
    0.36
    '
    0.36
     Pfer
    0.35
     lab
    0.35
    ..
    0.35
     last
    0.34
     my
    0.34
     I
    0.34
    Act Density 0.370%

    No Known Activations