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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "nod" and its variations, indicating agreement or acknowledgment

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

    nodding in agreement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    6
    -0.44
    mathrm
    -0.41
     
    -0.41
    \
    -0.39
    :
    -0.38
     extremely
    -0.38
    ​
    -0.38
     The
    -0.37
    I
    -0.36
    ...
    -0.35
    POSITIVE LOGITS
     nods
    1.04
     Nod
    0.99
     queſta
    0.96
    Nod
    0.96
     nodding
    0.96
     nod
    0.93
     queſto
    0.90
     zwiſchen
    0.89
    <unused16>
    0.88
    <unused52>
    0.88
    Act Density 0.004%

    No Known Activations