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

    Neuronpedia

    INDEX
    Explanations

    references to identifiers, particularly in a programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <unused23>
    -1.32
    <unused14>
    -1.32
    <unused43>
    -1.32
     desmotivaciones
    -1.32
    <unused79>
    -1.32
    <unused41>
    -1.31
    <unused42>
    -1.31
    <unused28>
    -1.31
    [@BOS@]
    -1.31
    <unused16>
    -1.31
    POSITIVE LOGITS
    ↵↵
    0.76
    ↵
    0.72
    .
    0.68
     
    0.68
    ,
    0.65
     Below
    0.63
     "
    0.62
    -
    0.62
     (
    0.62
     {
    0.61
    Act Density 0.327%

    No Known Activations