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

    Neuronpedia

    INDEX
    Explanations

    the beginning of a document or significant section

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    richTextPanel
    -0.92
    Personensuche
    -0.92
     étoit
    -0.89
    DeleteBehavior
    -0.87
     '\\;'
    -0.79
    addCriterion
    -0.78
    Personendaten
    -0.77
     ſche
    -0.77
     démission
    -0.75
     neceff
    -0.73
    POSITIVE LOGITS
     cla
    0.48
    <bos>
    0.48
    phonie
    0.46
    9
    0.46
     l
    0.45
     $\
    0.45
     P
    0.45
    a
    0.45
    8
    0.44
    1
    0.44
    Act Density 0.028%

    No Known Activations