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

    Neuronpedia

    INDEX
    Explanations

    adverbs that describe intensity or manner

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     admittedly
    -0.15
    fty
    -0.14
     UIF
    -0.14
    ãĤ·ãĤ§
    -0.14
    outs
    -0.14
    ables
    -0.14
    eniz
    -0.14
    OOK
    -0.14
    FFFFFFFF
    -0.14
    izable
    -0.14
    POSITIVE LOGITS
     accurate
    0.19
     beautiful
    0.16
     proportion
    0.15
     aware
    0.15
    003
    0.15
    etter
    0.15
     efficient
    0.14
    ondheim
    0.14
     behaved
    0.14
    etler
    0.14
    Act Density 0.083%

    No Known Activations