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

    Neuronpedia

    INDEX
    Explanations

    terms related to location and security in data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rungsseite
    -1.37
    <unused74>
    -1.29
    <unused41>
    -1.29
    <unused43>
    -1.29
    <unused28>
    -1.28
    <unused23>
    -1.28
    <unused42>
    -1.28
    <unused68>
    -1.28
    [@BOS@]
    -1.28
    <unused14>
    -1.28
    POSITIVE LOGITS
    ↵
    0.72
    ↵↵
    0.70
     
    0.70
    ,
    0.69
    s
    0.69
    .
    0.66
     and
    0.66
     (
    0.65
      
    0.64
     S
    0.63
    Act Density 0.311%

    No Known Activations