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

    Neuronpedia

    INDEX
    Explanations

    instances of reported speech or quotations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Bench
    -0.17
     ‘
    -0.15
    bag
    -0.15
     (“
    -0.14
    :
    -0.14
    aec
    -0.14
    allen
    -0.13
    ãĥ¼ãĥij
    -0.13
    jaw
    -0.13
    avier
    -0.13
    POSITIVE LOGITS
     regarding
    0.18
    åıĤçħ§
    0.15
    BuilderInterface
    0.15
    OffsetTable
    0.15
     referring
    0.15
     "'.
    0.14
    Ľå»º
    0.14
     reference
    0.14
    ,"↵
    0.13
    ¦
    0.13
    Act Density 0.050%

    No Known Activations