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

    Neuronpedia

    INDEX
    Explanations

    references to data structures and dump outputs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ↵↵
    -0.36
    ↵
    -0.28
    <h1>
    -0.26
    __
    -0.25
    1
    -0.24
    This
    -0.23
    .
    -0.22
     clearly
    -0.22
      
    -0.22
    </h1>
    -0.22
    POSITIVE LOGITS
    SequentialGroup
    1.05
    <unused17>
    1.02
    <pad>
    1.01
    <unused1>
    1.01
    <unused68>
    1.01
    <unused79>
    1.01
    <unused43>
    1.01
    <unused28>
    1.01
    <unused14>
    1.01
    <unused21>
    1.01
    Act Density 0.533%

    No Known Activations