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

    Neuronpedia

    INDEX
    Explanations

    specific formatting or syntactical elements in code and scripts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     continúas
    -0.88
    tvguidetime
    -0.81
     Majefty
    -0.80
     <?=
    -0.75
     iſt
    -0.75
    ねば
    -0.73
    ++
    -0.71
    trường
    -0.71
    ortheast
    -0.70
     تضيفلها
    -0.70
    POSITIVE LOGITS
    ↵↵
    0.76
    <bos>
    0.75
    ↵
    0.61
    ↵↵↵
    0.59
    .
    0.58
     The
    0.57
    The
    0.57
     I
    0.55
    protoimpl
    0.54
     Somehow
    0.53
    Act Density 0.035%

    No Known Activations