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

    Neuronpedia

    INDEX
    Explanations

    the presence of the verb "is" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    purpose of this work

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     autorytatywna
    -1.03
    ########.
    -0.97
    tagHelperRunner
    -0.92
    <unused41>
    -0.87
    ੝
    -0.87
    <unused8>
    -0.87
    <unused52>
    -0.87
    <unused79>
    -0.87
    <unused74>
    -0.87
    [@BOS@]
    -0.86
    POSITIVE LOGITS
     itself
    0.35
    2
    0.33
      
    0.33
    y
    0.30
     \
    0.29
    <strong>
    0.28
    3
    0.28
     recherchez
    0.27
    1
    0.27
    _
    0.27
    Act Density 0.052%

    No Known Activations