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

    Neuronpedia

    INDEX
    Explanations

    HTML or markup elements in the content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    BeginInit
    -0.65
    .
    -0.57
    o
    -0.57
    ur
    -0.57
    ky
    -0.56
    form
    -0.52
     TO
    -0.52
    dat
    -0.51
    ẩn
    -0.51
    sto
    -0.50
    POSITIVE LOGITS
     itſelf
    1.01
     greateſt
    0.98
     houſe
    0.96
     myſelf
    0.96
     Diſ
    0.95
     ARXIV
    0.92
     themſelves
    0.91
    ſelf
    0.91
     Houſe
    0.90
     ſche
    0.90
    Act Density 0.245%

    No Known Activations