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

    Neuronpedia

    INDEX
    Explanations

    transitional phrases that indicate additional information or elaboration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    -valu
    -0.17
    eras
    -0.17
    sel
    -0.16
    ermen
    -0.15
    .mapbox
    -0.15
    ове
    -0.15
    run
    -0.14
    erm
    -0.14
    impse
    -0.14
    ldata
    -0.14
    POSITIVE LOGITS
    igham
    0.16
    845
    0.15
    alion
    0.15
    ardown
    0.15
    alice
    0.15
    peon
    0.14
    hangi
    0.13
    ãĥ³ãĤ¬
    0.13
    idia
    0.13
     Conveyor
    0.13
    Act Density 0.008%

    No Known Activations