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

    Neuronpedia

    INDEX
    Explanations

    topics related to legality and conditions surrounding actions or items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /
    -0.86
     W
    -0.56
     /
    -0.55
     B
    -0.52
    <eos>
    -0.52
    (
    -0.49
    ↵↵
    -0.48
     (
    -0.48
    .
    -0.48
     
    -0.48
    POSITIVE LOGITS
    AndEndTag
    1.26
    還是
    1.01
    还是
    0.97
     autorytatywna
    0.96
    Datuak
    0.94
    ſelves
    0.93
     itſelf
    0.92
     doubtnut
    0.90
    expandindo
    0.89
    ########.
    0.89
    Act Density 0.236%

    No Known Activations