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

    Neuronpedia

    INDEX
    Explanations

    terms related to statistical measures and rankings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rungsseite
    -1.47
    <unused23>
    -1.45
    <pad>
    -1.45
    <unused3>
    -1.44
    <unused43>
    -1.44
    <unused16>
    -1.44
    <unused42>
    -1.44
    <unused41>
    -1.44
    <unused8>
    -1.44
    <unused14>
    -1.44
    POSITIVE LOGITS
     
    0.65
    ,
    0.58
     ranking
    0.56
    <i>
    0.56
     ranked
    0.53
     the
    0.52
     Ranking
    0.52
    ↵↵
    0.50
    ↵
    0.49
     The
    0.49
    Act Density 0.375%

    No Known Activations