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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "text" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     in
    -0.35
    ,
    -0.34
     –
    -0.33
    ↵↵
    -0.33
    »,
    -0.32
     ->
    -0.32
    <eos>
    -0.31
     >
    -0.31
     '@/
    -0.30
    \"></
    -0.30
    POSITIVE LOGITS
    <unused74>
    0.94
    [@BOS@]
    0.94
    <unused41>
    0.94
    <unused79>
    0.94
    <unused8>
    0.94
    <pad>
    0.94
    <unused14>
    0.94
    <unused43>
    0.94
    <unused23>
    0.94
    <unused51>
    0.94
    Act Density 0.001%

    No Known Activations