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

    Neuronpedia

    INDEX
    Explanations

    expressions that indicate evidence or demonstration of ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ht
    -0.15
    ellan
    -0.15
    ëŀĢ
    -0.14
    ak
    -0.14
     strictly
    -0.14
     sinon
    -0.13
    imer
    -0.13
    yte
    -0.13
     minimum
    -0.13
    ston
    -0.13
    POSITIVE LOGITS
     throughout
    0.23
     nowhere
    0.20
     everywhere
    0.19
    OffsetTable
    0.18
    sthrough
    0.18
     whenever
    0.17
     graph
    0.17
    ernes
    0.17
     through
    0.17
     loud
    0.16
    Act Density 0.094%

    No Known Activations