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

    Neuronpedia

    INDEX
    Explanations

    instances of agreement or acknowledgment gestures, particularly nodding

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     nodded
    -0.84
     nod
    -0.70
     nods
    -0.68
     nodding
    -0.57
    nod
    -0.40
     Nod
    -0.38
    Nod
    -0.36
     node
    -0.34
    Node
    -0.33
    node
    -0.33
    POSITIVE LOGITS
    AndEndTag
    1.09
    <unused43>
    1.00
    <unused41>
    1.00
    <pad>
    1.00
    <unused79>
    1.00
    ſſung
    1.00
    <unused16>
    1.00
    <unused74>
    1.00
    <unused8>
    1.00
    [@BOS@]
    1.00
    Act Density 0.001%

    No Known Activations