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

    Neuronpedia

    INDEX
    Explanations

    annotations and package specifications in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ↵
    -0.73
    ↵↵
    -0.63
    1
    -0.58
    2
    -0.57
     
    -0.55
    ,
    -0.55
    -
    -0.55
    te
    -0.53
      
    -0.53
    an
    -0.52
    POSITIVE LOGITS
     queſta
    1.41
    <unused43>
    1.34
    <pad>
    1.34
    <unused41>
    1.33
    <unused23>
    1.32
    <unused16>
    1.32
    <unused28>
    1.32
    <unused42>
    1.32
    [@BOS@]
    1.32
    <unused3>
    1.32
    Act Density 0.317%

    No Known Activations