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

    Neuronpedia

    INDEX
    Explanations

    technical terminology related to measurements and specifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     MainAxisSize
    -0.95
     ſeveral
    -0.87
     Jefus
    -0.86
     myſelf
    -0.85
     Majefty
    -0.85
     themſelves
    -0.84
    neſs
    -0.84
     utafitiHapana
    -0.84
     Monfieur
    -0.82
     pleaſure
    -0.79
    POSITIVE LOGITS
    ,
    0.51
    <eos>
    0.49
     (
    0.49
     
    0.45
    ↵↵
    0.42
     to
    0.41
     loạn
    0.40
     ,
    0.38
     Grand
    0.38
    使其
    0.38
    Act Density 1.909%

    No Known Activations